HK1207199B - Methods and systems for managing adaptation data - Google Patents

Description

Method and system for managing adaptation data

Inventor:

Royce A. Levien

Richard T. Lord

Robert W. Lord

Mark A. Malamud

Cross-references to related applications

If an Application Data Sheet (ADS) was filed on the filing date of this application, the Application Data Sheet is incorporated herein by reference. Any application claiming priority under 35 U.S.C. §§119, 120, 121, or 365(c) on the basis of the ADS, and any and all parent, grandfather, great-grandfather, etc. applications of such applications, are also incorporated herein by reference, including any priority claims made in those applications and any material incorporated by reference, to the extent such subject matter is not inconsistent herewith.

Related application :

This application is related to and/or claims the benefit of the earliest available effective filing date, if any, of the applications listed below (the "priority applications") (e.g., claiming the benefit of any and all parent, grandfather, or great-grandfather applications of the priority applications in addition to the earliest available priority date of the provisional patent application or claiming the benefit of 35 U.S.C. §§119(e) with respect to the provisional patent application). In addition, this application is related to "related applications," if any, which are listed below.

Priority application :

For purposes of additional USPTO statutory requirements, this application constitutes a continuation-in-part of U.S. patent application Ser. No. 13/538,866, entitled SPEECH RECOGNITION ADAPTATION SYSTEMS BASED ON ADAPTATION DATA, inventors Royce A. Levien, Richard T. Lord, Robert W. Lord, and Mark A. Malamud, filed Jun. 29, 2012, under Attorney Docket No. 0711-003-042-C00001, which is currently co-pending or is an application that is eligible for the benefit of the filing date of a currently co-pending application; and a continuation-in-part of U.S. patent application Ser. No. 13/538,855, entitled SPEECH RECOGNITION ADAPTATION SYSTEMS BASED ON ADAPTATION DATA, inventors Royce A. Levien, Richard T. Lord, Robert W. Lord, and Mark A. Malamud. A. Malamud, filed on June 29, 2012 under Mandate No. 0711-003-042-000000.

For purposes of additional USPTO statutory requirements, this application constitutes a continuation-in-part of U.S. patent application Ser. No. 13/564,649, entitled SPEECH RECOGNITION ADAPTATION SYSTEMS BASED ON ADAPTATION DATA, inventors Royce A. Levien, Richard T. Lord, Robert W. Lord, and Mark A. Malamud, filed Aug. 1, 2012, under Attorney Docket No. 0711-003-043-C00001, which is currently co-pending or is an application that is eligible for the benefit of the filing date of a currently co-pending application; and a continuation-in-part of U.S. patent application Ser. No. 13/564,647, entitled SPEECH RECOGNITION ADAPTATION SYSTEMS BASED ON ADAPTATION DATA, inventors Royce A. Levien, Richard T. Lord, Robert W. Lord, and Mark A. Malamud. A. Malamud, filed on August 1, 2012 under Mandate No. 0711-003-043-000000.

For purposes of additional USPTO statutory requirements, this application constitutes a continuation-in-part of U.S. patent application Ser. No. 13/564,651, entitled SPEECH RECOGNITION ADAPTATION SYSTEMS BASED ON ADAPTATION DATA, inventors Royce A. Levien, Richard T. Lord, Robert W. Lord, and Mark A. Malamud, filed Aug. 1, 2012, under Attorney Docket No. 0711-003-044-C00001, which is currently co-pending or is an application that is eligible for the benefit of the filing date of a currently co-pending application; and a continuation-in-part of U.S. patent application Ser. No. 13/564,650, entitled SPEECH RECOGNITION ADAPTATION SYSTEMS BASED ON ADAPTATION DATA, inventors Royce A. Levien, Richard T. Lord, Robert W. Lord, and Mark A. Malamud. A. Malamud, filed on August 1, 2012 under Mandate No. 0711-003-044-000000.

For purposes of additional USPTO statutory requirements, this application constitutes a continuation-in-part of U.S. patent application Ser. No. 13/609,142, entitled METHODS AND SYSTEMS FOR SPEECH ADAPTATION DATA, inventors Royce A. Levien, Richard T. Lord, Robert W. Lord, and Mark A. Malamud, filed Sep. 10, 2012, under Attorney Docket No. 0711-003-045-C00001, which is currently co-pending or is an application that is eligible for the benefit of the filing date of a currently co-pending application; and a continuation-in-part of U.S. patent application Ser. No. 13/609,139, entitled METHODS AND SYSTEMS FOR SPEECH ADAPTATION DATA, inventors Royce A. Levien, Richard T. Lord, Robert W. Lord, and Mark A. Malamud. A. Malamud, filed on September 10, 2012 under Mandate No. 0711-003-045-000000.

For purposes of additional USPTO statutory requirements, this application constitutes a continuation-in-part of U.S. patent application Ser. No. 13/609,145, entitled METHODS AND SYSTEMS FOR SPEECH ADAPTATION DATA, inventors Royce A. Levien, Richard T. Lord, Robert W. Lord, and Mark A. Malamud, filed Sep. 10, 2012, under Attorney Docket No. 0711-003-046-C00001, which is currently co-pending or is an application that is eligible for the benefit of the filing date of a currently co-pending application; and a continuation-in-part of U.S. patent application Ser. No. 13/609,143, entitled METHODS AND SYSTEMS FOR SPEECH ADAPTATION DATA, inventors Royce A. Levien, Richard T. Lord, Robert W. Lord, and Mark A. Malamud. A. Malamud, filed on September 10, 2012 under Mandate No. 0711-003-046-000000.

The United States Patent Office (USPTO) has published an effective notice that the USPTO's computer program requires patent applicants to both cite a serial number and indicate whether the application is a continuation, continuation-in-part, or division of a parent application. Stephen G. Kunin, Benefit of Prior-Filed Applications, USPTO Official Gazette, March 18, 2003. The USPTO has further provided a format for an application data sheet that allows for automatic loading of bibliographic data but requires identification of each application as a continuation, continuation-in-part, or division of a parent application. The present applicant entity (hereinafter referred to as "applicant") has previously provided specific citations to the applications from which priority is claimed under the statute. Applicant understands that the statute is unambiguous as to its specific citation language and does not require a serial number or any characterization, such as "continuation" or "continuation-in-part," to claim priority to a U.S. patent application. Notwithstanding the foregoing, Applicant understands that the USPTO's computer programs have certain data entry requirements and, accordingly, Applicant has provided designations of the relationship between this application and its parent applications as previously described and in any ADS filed with this application, but expressly notes that these designations are not to be construed in any way as any kind of comment and/or admission as to whether this application contains any new matter beyond that of its parent applications.

To the extent that the list of applications given above is inconsistent with the list provided via the ADS, applicant intends to claim priority from each application appearing in the Priority Applications section of the ADS and from each application appearing in the Priority Applications section of the present application.

All subject matter of the priority application and related applications, and any and all parent, grandfather, and great-grandfather applications of the priority application and related applications, including any priority claims, is incorporated herein by reference to the extent such subject matter is not inconsistent herewith.

background

This application relates to adaptation data.

Summary of the Invention

In one or more various aspects, a method includes, but is not limited to, managing adaptation data, wherein the adaptation data is associated with at least one aspect of speech by a particular party, facilitating transmission of the adaptation data to a target device in response to an indication associated with a speech-facilitated transaction with the particular party, wherein the adaptation data is associated with at least one aspect of speech by the particular party, and determining whether to update the adaptation data, the determination being based at least in part on a result of at least a portion of the speech-facilitated transaction. In addition to the foregoing, further method aspects are described in the claims, drawings, and text forming a part of the disclosure set forth herein.

The claims, description, and drawings of this application may describe one or more of the present technologies in operational/functional language, for example, as a set of operations to be performed by a computer. In most cases, such operational/functional descriptions will be understood by those skilled in the art to refer to specially configured hardware (e.g., since a general-purpose computer becomes a special-purpose computer once it is programmed to perform specific functions following instructions from program software).

Importantly, while the operational/functional descriptions described herein are understandable to the human mind, they are not abstract concepts of operations/functions separate from the computational implementation of those operations/functions. Rather, these operations/functions represent specifications of quite complex computing machines or other devices. As discussed in detail below, operational/functional language must be read in its proper technical context, i.e., as a concrete specification of a physical implementation.

The logical operations/functions described herein are abstractions of the machine specifications or other physical mechanisms specified by the operations/functions, so that the otherwise incomprehensible machine specifications can be grasped by the human mind. This abstraction also allows those skilled in the art to adapt the operational/functional description of the technology across many different vendor-specific hardware configurations or platforms, rather than being limited to a particular vendor's hardware configuration or platform.

Some current technical descriptions (e.g., detailed descriptions, drawings, claims, etc.) may be formulated in terms of logical operations/functions. As described in more detail in the following paragraphs, these logical operations/functions are not representations of abstract concepts, but rather representations of static or sequential specifications for various hardware components. Stated another way, unless the context indicates otherwise, logical operations/functions will be understood by those skilled in the art to represent static or sequential specifications for various hardware components. This is true because the tools available to those skilled in the art for implementing technical disclosures formulated in an operational/functional format—tools in the form of high-level programming languages (e.g., C, Java, Visual Basic, etc.) or tools in the form of Very High Speed Hardware Description Language (VHDL, a language for describing logic circuits using text—are generators of static or sequential specifications for various hardware configurations. This fact is sometimes obscured by the broad term "software." As illustrated in the following explanation, those skilled in the art understand that what is termed "software" is shorthand for quite complex interconnections/specifications of ordered physical elements. The term "ordered elements of matter" may refer to physical computing devices, such as components of electronic logic gates, molecular computing logic components, quantum computing mechanisms, etc.

For example, a high-level programming language is a programming language with strong abstractions, such as multiple layers of abstraction from the details of the machine's sequential organization, state, input, output, etc., that the high-level programming language actually specifies. See, for example, Wikipedia, "High-level programming language," http://en.wikipedia.org/wiki/High-level_programming_language (June 5, 2012, 21:00 GMT). To facilitate understanding, high-level programming languages are often similar to or even share notation with natural languages. See, for example, Wikipedia, "Natural language," http://en.wikipedia.org/wiki/Natural_language (June 5, 2012, 21:00 GMT).

It has been argued that because high-level programming languages use strong abstractions (e.g., they may share symbols with natural languages), they are therefore "purely mind-constructed" (e.g., "software"—computer programs or computer programming—is in some way an ineffable mind-construct because, at a high level of abstraction, it can be conceived and understood by the human mind). This argument has been used to characterize technical descriptions in the form of functions/operations as having a certain degree of "abstraction." In reality, this is not the case in technical fields (e.g., information and communications technology).

The fact that high-level programming languages use strong abstractions to facilitate human understanding should not be taken as an indication that the content expressed is an abstract concept. In fact, those skilled in the art understand that only the opposite is true. If a high-level programming language is a tool used to implement technical disclosures in the form of functions/operations, then those skilled in the art will understand that, far from being abstract, imprecise, "fuzzy," or "mental" in any significant semantic definition, such a tool is instead a nearly incomprehensible, precise sequential specification of a specific computing machine—parts of which are established by activating/selecting these parts over time (e.g., clock time) from a typical, more general computing machine. This fact is sometimes obscured by the superficial similarities between high-level programming languages and natural languages. These superficial similarities can also serve to gloss over the fact that high-level programming language implementations ultimately perform valuable work by creating/controlling many different computing machines.

The many different computing machines specified by high-level programming languages are almost unimaginably complex. Fundamentally, the hardware used in computing machines is typically composed of some type of ordered matter (e.g., traditional electronic devices (e.g., transistors), deoxyribonucleic acid (DNA), quantum devices, mechanical switches, optical systems, fluidics, pneumatics, optical devices (e.g., optical interferometers), molecules, etc.) configured to form logic gates. Logic gates are generally physical devices that can be actuated electrically, mechanically, chemically, or in some other manner to change physical states to form the physical reality of Boolean logic.

Logic gates can be configured to form a logic circuit, which is generally a physical device that can be driven electrically, mechanically, chemically, or otherwise to form the physical reality of some logical function. Types of logic circuits include devices such as multiplexers, registers, arithmetic logic units (ALUs), computer memories, etc., each of which can be combined to form yet other types of physical devices, such as central processing units (CPUs), the most widely known of which are microprocessors. Modern microprocessors often contain more than 100 million logic gates (and often more than 1 billion transistors) in their many logic circuits. See, for example, Wikipedia, Logic gate, http://en.wikipedia.org/wiki/Logic_gates (June 5, 2012, 21:03 GMT).

The logic circuits forming a microprocessor are configured to provide a microarchitecture that will execute instructions defined by the microprocessor's instruction set architecture. The instruction set architecture is the portion of the microprocessor's architecture associated with programming, including primitive data types, instructions, registers, addressing modes, memory architecture, interrupt and exception handling, and external input/output. See, for example, Wikipedia, Computer architecture, http://en.wikipedia.org/wiki/Computer_architecture (June 5, 2012, 21:03 GMT).

The instruction set architecture includes a specification for a machine language that a programmer can use to use/control a microprocessor. Because machine language instructions make them directly executable by a microprocessor, they are typically composed of strings of binary numbers or bits. For example, a typical machine language instruction can be many bits long (e.g., 32, 64, or 128 bit strings are currently common). A typical machine language instruction may appear in the form of "11110000101011110000111100111111" (a 32-bit instruction).

What's important here is that, although machine language instructions are written as sequences of binary numbers, these binary numbers actually specify physical reality. For example, if certain semiconductors are used to physically implement Boolean logic operations, it becomes apparent that the mathematical bits "1" and "0" in a machine language instruction actually constitute shorthand for specifying that a specific voltage be applied to a specific wire. For example, in certain semiconductor technologies, a binary number "1" (e.g., a logical "1") in a machine language instruction specifies a voltage of approximately +5 volts applied to a specific "wire" (e.g., a metal trace on a printed circuit board), while a binary number "0" (e.g., a logical "0") in a machine language instruction specifies a voltage of approximately -5 volts applied to a specific "wire." In addition to specifying the voltages configured for the machine, these machine language instructions also select and activate specific sets of logic gates from among the millions of logic gates in a more general machine. Thus, far from being an abstract mathematical expression, a program of machine language instructions (even if written as a string of 0s and 1s) can specify many, many configured physical machines or states of physical machines.

Machine language is generally incomprehensible to most people (for example, the previous example is just one instruction, and some personal computers execute 2 billion instructions per second). See, for example, Wikipedia, "Instructions per second," http://en.wikipedia.org/wiki/Instruction_per_second (June 5, 2012, 9:04 PM GMT). Consequently, programs written in machine language—which can be tens of millions of machine language instructions long—are difficult to understand. In response to this, early assembly languages were developed, which used mnemonics to point to machine language instructions rather than directly using their numerical values. For example, to perform a multiplication operation, programmers coded the abbreviation "mult," which represents the binary number "011000" in MIPS machine code. Although assembly language initially helped people control microprocessors to perform tasks, over time, the complexity of the tasks required of people exceeded their ability to control microprocessors using assembly language alone.

At this point, it's important to note that the same tasks need to be done over and over again, and the machine language required to complete these repetitive tasks is the same. With this in mind, compilers were developed. A compiler is a device that takes statements that are easier for humans to understand than machine or assembly language (e.g., "add 2 + 2 and output the result") and converts these human-understandable statements into complex, lengthy, and massive machine language code (e.g., millions of 32-, 64-, or 128-bit strings). Compilers thus convert high-level programming languages into machine language.

This compiled machine language, as previously mentioned, is then used as a technical specification to sequentially construct and cause many different computing machines to interoperate, thereby performing useful, tangible, and concrete tasks for humans. For example, as previously noted, this machine language—a compiled version of a higher-level language—serves as a technical specification that selects hardware logic gates, specifies voltage levels, timing of voltage transitions, and so forth, in order to perform useful tasks for humans through hardware.

Thus, when viewed by one skilled in the art, functional/operational technical descriptions are far from abstract concepts. Rather, such functional/operational technical descriptions, when understood through tools available in the industry, such as those just described, can be understood as human-understandable representations of hardware specifications, the complexity and specificity of which far exceed the comprehension of most people. In light of this, one skilled in the art will understand that any such operational/functional technical description—given the disclosure herein and the knowledge of one skilled in the art—can be understood as operations put into physical reality through: (a) one or more interconnected physical machines; (b) interconnected logic gates configured to form one or more physical machines, representing sequential/combinatorial logic; (c) interconnected ordered matter (e.g., interconnected electronic devices (e.g., transistors), DNA, quantum devices, mechanical switches, optical systems, fluidics, pneumatics, molecules, etc.) constituting logic gates, which form a physical reality representing logic; or (d) any actual combination of the foregoing. In fact, any physical object with a stable, measurable, and mutable state can be used to construct a machine based on the foregoing technical descriptions. For example, Charles Babbage constructed the first computer out of wood and powered it by cranking a handle.

Thus, far from being understood as abstract ideas, those skilled in the art recognize functional/operational technical descriptions as human-understandable representations of one or more hardware instances of almost unimaginable complexity and chronological order. The fact that functional/operational technical descriptions may readily lend themselves to high-level computing languages (or high-level block diagrams for that matter) that share certain words, structures, terms, etc. with natural languages cannot simply be viewed as an indication that these functional/operational technical descriptions are abstract ideas or merely expressions of abstract ideas. In fact, as outlined herein, this is simply not true in the art. When viewed through the tools available to those skilled in the art, these functional/operational technical descriptions are viewed as specifying hardware configurations of almost unimaginable complexity.

As outlined above, the reasons for using functional/operational technical descriptions are at least twofold. First, using functional/operational technical descriptions allows machines of nearly infinite complexity and the machine operations resulting from interconnected hardware components to be described in a manner that the human mind can process (e.g., by mimicking natural language and logical narrative flow). Second, using functional/operational technical descriptions helps those skilled in the art understand the described subject matter by providing a description that is more or less independent of any particular vendor's hardware components.

The use of functional/operational technical descriptions assists those skilled in the art in understanding the described subject matter because, as is apparent from the discussion above, one can readily (though not quickly) rewrite the technical descriptions set forth in this document into trillions of ones and zeros, billions of single lines of assembly-level machine code, millions of logic gates, thousands of gate arrays, or any number of intermediate levels of abstraction. However, if any of these low-level technical descriptions were to replace the current technical description, those skilled in the art might encounter undue difficulty in implementing the present disclosure because such low-level technical descriptions might add complexity without corresponding benefit (e.g., by describing subject matter that utilizes the specifications of one or more vendor-specific hardware parts). Thus, the use of functional/operational technical descriptions assists those skilled in the art by separating the technical description from the specifications of any vendor-specific hardware parts.

In view of the foregoing, the logical operations/functions set forth in the present technical description are representations of static or sequential specifications of various ordered physical elements, in order to make these specifications understandable to the human mind and adjustable to produce a variety of hardware configurations. The logical operations/functions disclosed herein should be treated as such and should not be derogatorily reduced to abstract concepts simply because they present specifications that are readily understood by those skilled in the art and applied in a manner independent of a particular vendor's hardware implementation.

In one or more different aspects, one or more related systems may be implemented in a machine, composition of matter, or system of manufacture, which is limited to the subject matter allowable under 35 USC 101. The one or more related systems may include, but are not limited to, circuitry and/or programming for implementing the method aspects recited herein. The circuitry and/or programming may be any combination of hardware, software, and/or firmware configured to implement the method aspects recited herein, depending on the design choices of the system designer, and is limited to the subject matter allowable under 35 USC 101.

In one or more various aspects, a system includes, but is not limited to: means for managing adaptation data, wherein the adaptation data is associated with at least one aspect of speech by a particular party; means for facilitating transmission of the adaptation data to a target device in response to an indication of a speech-facilitating transaction associated with the particular party, wherein the adaptation data is associated with at least one aspect of speech by the particular party; and means for determining whether to update the adaptation data, the determination being based at least in part on a result of at least a portion of the speech-facilitating transaction. In addition to the foregoing, further system aspects are described in the claims, drawings, and text forming a part of the disclosure set forth herein.

In one or more various aspects, a system includes, but is not limited to, circuitry for managing adaptation data, wherein the adaptation data is associated with at least one aspect of speech by a particular party; circuitry for facilitating transmission of the adaptation data to a target device in response to an indication of a speech-facilitating transaction associated with the particular party, wherein the adaptation data is associated with at least one aspect of speech by the particular party; and circuitry for determining whether to update the adaptation data, the determination being based at least in part on a result of at least a portion of the speech-facilitating transaction. In addition to the foregoing, further system aspects are described in the claims, drawings, and text forming a part of the disclosure set forth herein.

In one or more various aspects, a computer program product includes a signal-bearing medium carrying one or more instructions, including, but not limited to: one or more instructions for managing adaptation data, wherein the adaptation data is associated with at least one aspect of speech by a particular party; one or more instructions for facilitating transmission of the adaptation data to a target device in response to an indication of a speech-facilitating transaction associated with the particular party, wherein the adaptation data is associated with at least one aspect of speech by the particular party; and one or more instructions for determining whether to update the adaptation data, the determination being based at least in part on a result of at least a portion of the speech-facilitating transaction. In addition to the foregoing, further computer program product aspects are described in the claims, drawings, and text forming a part of the disclosure set forth herein.

In one or more different aspects, a device is defined by a computing language such that the device includes: one or more interconnected physical machines sequenced to manage adaptation data, wherein the adaptation data is associated with at least one aspect of speech by a particular party; one or more interconnected physical machines sequenced to transmit the adaptation data to a target device in response to an indication of a speech-facilitating transaction associated with the particular party, wherein the adaptation data is associated with at least one aspect of speech by the particular party; and one or more interconnected physical machines sequenced to determine whether to update the adaptation data, the determination being based at least in part on a result of at least a portion of the speech-facilitating transaction.

In addition to the foregoing, various other method and/or system and/or program product aspects are set forth and described in the teachings, such as in the text of the present disclosure (eg, claims and/or detailed description) and/or figures.

The foregoing is an overview and therefore may contain simplifications, generalizations, inclusions, and/or omissions of details; consequently, those skilled in the art will appreciate that this overview is illustrative only and is not intended to be limiting in any way. Other aspects, features, and advantages of the devices and/or processes and/or other subject matter described herein will become apparent by reference to the detailed description, the accompanying drawings, and/or the teachings presented herein.

BRIEF DESCRIPTION OF THE DRAWINGS

For a more complete understanding of the embodiments, reference is now made to the following description in conjunction with the accompanying drawings. The use of the same reference numerals in different figures generally indicates similar or identical components, unless the context indicates otherwise. The illustrative embodiments described in the detailed description, drawings, and claims are not intended to be limiting. Other embodiments may be utilized and other changes may be made without departing from the spirit or scope of the subject matter presented herein.

FIG1A illustrates a high-level block diagram of an exemplary environment 100 , according to one embodiment.

FIG. 1B illustrates a high-level block diagram of a personal device 120 operating in the exemplary embodiment 100 , according to one embodiment.

FIG1C illustrates a high-level diagram of an exemplary environment 100', which is an example of an exemplary embodiment 100 having a personal device 120, according to an embodiment.

FIG. 1D illustrates a high-level diagram of an exemplary environment 100 ″, which is an example of an exemplary embodiment 100 having a personal device 120 , according to an embodiment.

FIGURE 1E illustrates a high-level diagram of an exemplary environment 100'" which is an example of an exemplary embodiment 100 having a personal device 120, according to an embodiment.

FIG. 2 , comprising FIG. 2A-2B , illustrates particular aspects of speech adaptation data associated with at least one aspect of a particular party adaptation module 152 of a personal device 120 of the environment 100 of FIG. 1B .

3 , comprising FIGS. 3A-3D , illustrates certain aspects of the speech-adapted data transfer facilitation module 154 of the personal device 120 of the environment 100 of FIG. 1B in response to an indication of a speech-facilitated transaction including a target device.

4, including FIGs. 4A-4I, illustrates certain aspects of the speech adaptation data potential correction determination module 156 of the personal device 120 of the environment 100 of FIG. 1B based, in part, on the results of a portion of a speech-facilitated transaction.

FIG5 is a high-level logical flow diagram of a process (eg, operational flow 500 ) according to an embodiment.

FIG6A is a high-level logical flow diagram depicting a method of an alternative implementation of the manage adaptation data operation 502 of FIG5 , according to one or more embodiments.

FIG6B is a high-level logic flow diagram depicting a method of an alternative implementation of the manage adaptation data operation 502 of FIG5 , according to one or more embodiments.

FIG7A is a high-level logical flow diagram depicting a method that facilitates an alternative implementation of transmitting the adaptation data 504 of FIG5 , according to one or more embodiments.

FIG7B is a high-level logic flow diagram depicting a method that facilitates an alternative implementation of transmitting the adaptation data 504 of FIG5 , according to one or more embodiments.

FIG7C is a high-level logic flow diagram depicting a method that facilitates an alternative implementation of transmitting the adaptation data 504 of FIG5 , according to one or more embodiments.

FIG7D is a high-level logic flow diagram depicting a method that facilitates an alternative implementation of transmitting the adaptation data 504 of FIG5 , according to one or more embodiments.

FIG8A is a high-level logic flow diagram illustrating a method for determining whether to update the adaptation data 506 of FIG5 , according to one or more embodiments.

FIG8B is a high-level logic flow diagram illustrating a method for determining whether to update the adaptation data 506 of FIG5 , according to one or more embodiments.

FIG8C is a high-level logic flow diagram illustrating a method for determining whether to update the adaptation data 506 of FIG5 according to one or more embodiments.

FIG8D is a high-level logic flow diagram illustrating a method for determining whether to update the adaptation data 506 of FIG5 according to one or more embodiments.

FIG8E is a high-level logic flow diagram illustrating a method for determining whether to update the adaptation data 506 of FIG5 according to one or more embodiments.

FIG8F is a high-level logic flow diagram illustrating a method for determining whether to update the adaptation data 506 of FIG5 according to one or more embodiments.

FIG8G is a high-level logic flow diagram illustrating a method for determining whether to update the adaptation data 506 of FIG5 according to one or more embodiments.

FIG8H is a high-level logic flow diagram illustrating a method for determining whether to update the adaptation data 506 of FIG5 according to one or more embodiments.

FIG8I is a high-level logic flow diagram illustrating a method for determining whether to update the adaptation data 506 of FIG5 according to one or more embodiments.

DETAILED DESCRIPTION

In the following detailed description, reference is made to the accompanying drawings, which form a part thereof. In the drawings, like symbols generally indicate similar or identical components or items, unless the context indicates otherwise. The illustrative embodiments described in the detailed description, drawings, and claims are not intended to be limiting. Other embodiments may be utilized, and other changes may be made, without departing from the spirit or scope of the subject matter presented herein.

Thus, according to various embodiments, computer-implemented methods, systems, circuits, articles, ordered connections of matter, and computer program products are designed to: provide, among other things, an interface for managing adaptation data, wherein the adaptation data is associated with at least one aspect of speech by a particular party; facilitate the transmission of adaptation data to a target device in response to an indication of a transaction associated with speech-facilitating transaction by a particular party, wherein the adaptation data is associated with at least one aspect of speech by the particular party; and determine whether to update the adaptation data, the determination being based at least in part on the results of at least a portion of the speech-facilitating transaction.

This application uses formal outline headings for clarity. However, it should be understood that these outline headings are for presentation purposes and that different types of subject matter may be discussed throughout the application (e.g., a device/structure may be described under a process/operation heading and/or a process/operation may be discussed under a structure/process heading; and/or the description of a single topic may span two or more headings). Therefore, the use of formal outline headings is not intended to be limiting in any way.

Throughout this application, examples and lists are given with parentheses, the abbreviation "such as," or both. Unless expressly stated otherwise, these examples and lists are illustrative only and not exhaustive. In most cases, it is impractical to list every example and every combination. Therefore, smaller illustrative lists and examples are used that focus on providing an understanding of the claim terms rather than limiting the scope of these terms.

With respect to the use of substantially any plural and/or singular terms herein, those skilled in the art can translate from the plural to the singular and/or from the singular to the plural as appropriate to the context and/or application. The various singular/plural permutations are not explicitly set forth herein for the sake of clarity.

Those skilled in the art will recognize that the components (e.g., operations), devices, objects, and the accompanying discussions described herein are used as examples for conceptual clarity and contemplate a variety of configuration modifications. Consequently, as used herein, the specific examples and accompanying discussions set forth are intended to represent their more general categories. In general, the use of any specific example is intended to represent its category, and the non-inclusion of specific components (e.g., operations), devices, and objects should not be considered limiting.

This application uses formal outline headings for clarity. However, it should be understood that the outline headings are for presentation purposes and that different types of subject matter may be discussed throughout this application (e.g., a device/structure may be described under a process/operation heading and/or a process/operation may be discussed under a structure/process heading; and/or the description of a single topic may span two or more headings). Therefore, the use of formal outline headings is not intended to be limiting in any way.

Although user 105 is illustrated/described herein as a single illustrated person, those skilled in the art will appreciate that user 105 may represent a human user, a robotic user (e.g., a computing entity), and/or substantially any combination thereof (e.g., a user may be assisted by one or more robotic agents), unless the context indicates otherwise. Those skilled in the art will appreciate that, generally speaking, the same entity may be referred to as a "sender" and/or other entity-oriented terms (as such terms are used herein) unless the context indicates otherwise.

Those skilled in the art will recognize that the state of the art has advanced to the point where there is minimal differentiation between hardware, software, and/or firmware implementations of various aspects of a system; the use of hardware, software, and/or firmware is often (but not always, as the choice between hardware and software may become important in certain contexts) a design choice that represents a cost versus efficiency tradeoff. Those skilled in the art will understand that there are a variety of vehicles by which the processes and/or systems and/or other techniques described herein can be implemented (e.g., hardware, software, and/or firmware), and that the preferred vehicle may vary depending on the context in which the processes and/or systems and/or other techniques are deployed. For example, if the implementer determines that speed and accuracy are paramount, the implementer may select a primarily hardware and/or firmware vehicle; alternatively, if flexibility is paramount, the implementer may select a primarily software implementation; or again, the implementer may select some combination of hardware, software, and/or firmware in one or more machines, combinations of materials, and articles of manufacture, limited to subject matter patentable under 35 USC §101. Thus, there are several possible carriers by which the processes and/or devices and/or other techniques described herein may be implemented, with no one carrier being inherently superior to the other, as any carrier to be utilized is a choice dependent upon the context in which the carrier will be deployed and the implementer's particular considerations (e.g., speed, flexibility, or predictability), any of which are variable. Those skilled in the art will recognize that the optical aspects of the implementation will generally employ optically oriented hardware, software, and firmware.

In some implementations described herein, logic and similar implementations may include software or other control structures. For example, an electronic circuit may have one or more current paths constructed and arranged to implement various functions as described herein. In some implementations, one or more media may be configured to carry device-detectable implementations when the media holds or sends device-detectable instructions executed as described herein. In some variations, for example, the implementation may include an update or modification of existing software or hardware or gate arrays or programmable hardware, such as the reception or transmission of one or more instructions performed in association with one or more operations described herein. Alternatively or in addition, in some variations, the implementation may include dedicated hardware, software, firmware devices and/or general-purpose devices that execute or otherwise call dedicated devices. The specification or other implementation may be transmitted via one or more instances of a tangible transmission medium as described herein, optionally transmitted multiple times via packet transmission or via distributed media.

Alternatively or in addition, implementation may include executing a dedicated instruction sequence or calling circuitry to enable, trigger, coordinate, request, or otherwise cause one or more occurrences of virtually any functional operation described herein. In some variations, the operational or other logical descriptions herein may be expressed as source code and compiled or called as an executable instruction sequence. In some contexts, for example, implementation may be provided in whole or in part via source code or other code sequences such as C++. In other implementations, source code or other code implementations, using commercially available and/or industry-proven techniques, may be compiled/implemented/translated/converted into a high-level descriptor language (e.g., initially implementing the techniques described in a C or C++ programming language and subsequently converting the programming language implementation into a logically synthesizable language implementation, a hardware description language implementation, a hardware design simulation implementation, and/or other such similar expression patterns). For example, some or all of the logical expression (e.g., a computer programming language implementation) may be displayed as a Verilog-type hardware description (e.g., via a hardware description language (HDL) and/or a very high speed integrated circuit hardware descriptor language (VHDL)) or other circuit model, which may then be used to generate a physical implementation with hardware (e.g., an application-specific integrated circuit). Given these teachings, one skilled in the art will understand how to obtain, configure, and optimize appropriate transmission or computing elements, material supplies, actuators, or other structures.

Those skilled in the art will recognize that it is common in the industry to implement devices and/or processes and/or systems and then use engineering design and/or other practices to integrate these implemented devices and/or processes and/or systems into broader devices and/or processes and/or systems. That is, at least a portion of the devices and/or processes and/or systems described herein can be integrated into other devices and/or processes and/or systems through a reasonable amount of experimentation. Those skilled in the art will recognize that examples of these other devices and/or processes and/or systems may include, as appropriate to the context and application, all or part of the following devices and/or processes and/or systems: (a) air transportation (e.g., airplanes, rockets, helicopters, etc.); (b) ground transportation (e.g., cars, trucks, trains, tanks, armored personnel carriers, etc.); (c) buildings (e.g., homes, warehouses, offices, etc.); (d) facilities (e.g., refrigerators, washers, dryers, etc.); (e.g., networking systems, telephone systems, voice over IP systems, etc.); (f) business entities (e.g., Internet Service Provider (ISP) entities, such as Comcast Cable, Qwest, Southwestern Bell, etc.) or (g) wired/wireless service entities (e.g., Sprint, Cingular, Nextel, etc.), etc.

In some cases, use of a system or method may occur within a region even if components are located outside of the region. For example, in the context of distributed computing, use of a distributed computing system may occur within a region even if components of the system may be located outside of the region (e.g., repeaters, servers, processors, signal-carrying media, sending computers, receiving computers, etc. may be located outside of the region).

Sales of a system or method may also occur within a territory even if components of the system or method are located and/or used outside the territory. Furthermore, implementing at least a portion of a system for performing a method in one territory does not preclude use of the system in another territory.

Those skilled in the art will recognize that for the sake of conceptual clarity, the components (e.g., operations), devices, objects, and the accompanying discussions described herein are used as examples, and various configuration modifications are contemplated. Consequently, as used herein, the specific examples and accompanying figure descriptions set forth are intended to represent their more general classes. In general, the use of any specific example is intended to represent its class, and the non-inclusion of specific components (e.g., operations), devices, and objects should not be considered limiting.

The subject matter described herein sometimes illustrates different components that are contained in or connected to different other components. It should be noted that the architectures described are merely exemplary and in fact many other structures that can be used to obtain the same function can be adopted. In a conceptual sense, any composition arrangement that obtains the same function is effectively "associated" to obtain the required function. Therefore, any two compositions that are combined to obtain a specific function herein can be considered to be "associated" to obtain the required function, regardless of the architecture or intermediate components. Similarly, any two components that are so associated can also be considered to be "operably connected" or "operably coupled" to obtain the required function, and any two components that can be so associated can also be considered to be "operably coupled" to obtain the required function. Specific examples of operable coupling include, but are not limited to, components that can physically match and/or physically interact, and/or components that can wirelessly interact, and/or components that can wirelessly interact, and/or logically interact, and/or components that can logically interact.

In some cases, one or more components may be referred to herein as being "configured to," "configured by," "configurable to," "operating/acting to," "suitable for/adaptable to," "capable of," "complying/complying with," etc. Those skilled in the art will understand that these terms (e.g., "configured to") generally encompass active state components and/or inactive state components and/or standby state components, unless the context requires otherwise.

In a general sense, those skilled in the art will recognize that the various embodiments described herein may be implemented individually and/or collectively with various types of electro-mechanical systems having a wide range of electrical components, such as hardware, software, firmware, and/or virtually any combination thereof, which are limited to subject matter patentable under 35 USC 101; and a wide range of components that can impart mechanical force or motion to devices such as rigid bodies, spring or torsion bodies, hydraulic, electromagnetic actuation, and/or virtually any combination thereof. Consequently, as used herein, "electromechanical system" includes, but is not limited to, circuits operatively coupled to transducers (e.g., actuators, motors, piezoelectric crystals, microelectromechanical systems (MEMS), etc.), circuits having at least one discrete circuit, circuits having at least one integrated circuit, circuits having at least one application specific integrated circuit, circuits forming a general purpose computing device configured by a computer program (e.g., a general purpose computer configured by a computer program that at least partially performs the processes and/or apparatus described herein, or a microprocessor configured by a computer program that at least partially performs the methods and/or apparatus described herein), circuits forming a storage device (e.g., forming memory (e.g., random access, flash, read-only, etc.)), circuits forming a communication device (e.g., a modem, a communication switch, an opto-electronic device, etc.), and/or any non-electrical analogues therein, such as optical or other analogues (e.g., graphene-based circuits). One skilled in the art will also appreciate that examples of electromechanical systems include, but are not limited to, numerous consumer electronic systems, medical devices, and other systems such as motor transport systems, factory automation systems, security systems, and/or communication/computing systems. Those skilled in the art will recognize that electro-mechanical devices as described herein are not necessarily limited to systems that are both electrically and mechanically actuated, unless the context indicates otherwise.

In a general sense, those skilled in the art will recognize that the various aspects described herein, which may be implemented individually and/or collectively by a wide range of hardware, software, firmware, and/or any combination thereof, may be considered to be comprised of various types of "circuits." Thus, as used herein, "circuitry" includes, but is not limited to, circuitry having at least one discrete circuit, circuitry having at least one integrated circuit, circuitry having at least one application-specific integrated circuit, circuitry forming a general-purpose computing device configured by a computer program (e.g., a general-purpose computer configured by a computer program that at least partially performs the processes and/or devices described herein, or a microprocessor configured by a computer program that at least partially performs the processes and/or devices described herein), circuitry forming a storage device (e.g., circuitry forming memory (e.g., random access, flash memory, read-only, etc.)), and/or circuitry forming a communication device (e.g., a modem, a communication switch, an optical-to-electronic device, etc.). Those skilled in the art will recognize that the subject matter described herein may be implemented in analog or digital form, or some combination thereof.

Those skilled in the art will recognize that at least a portion of the devices and/or processes described herein can be integrated into an image processing system. Those skilled in the art will recognize that a typical image processing system generally includes one or more of the following components: a system unit housing; a video display device; a memory such as volatile memory or non-volatile memory; a processor such as a microprocessor or a digital signal processor; a computing entity such as an operating system, drivers, and application programs; one or more interactive devices (e.g., a touch pad, a touch screen, an antenna, etc.); a control system including feedback loops and control motors (e.g., feedback for sensing lens position and/or velocity; control motors for moving/distorting the lens to provide the desired focus). The image processing system can be implemented using suitable commercially available components, such as those typically found in digital still systems and/or digital motion systems.

Those skilled in the art will recognize that at least a portion of the devices and/or processes described herein can be integrated into a data processing system. Those skilled in the art will recognize that a data processing system generally includes one or more of the following components: a system unit housing; a video display device; a memory such as volatile memory or non-volatile memory; a processor such as a microprocessor or a digital signal processor; a computing entity such as an operating system, drivers, a graphical user interface, and application programs; one or more interactive devices (e.g., a touch pad, a touch screen, an antenna, etc.); and/or a control system including feedback loops and control motors (e.g., feedback for sensing position and/or velocity; control motors for moving and/or adjusting devices and/or quantities). The data processing system can be implemented using suitable commercially available components, such as those typically found in data computing/communication and/or network computing/communication systems.

For the purposes of this application, "cloud" computing may be understood as described in the cloud computing literature. For example, cloud computing may be a method and/or system for delivering computing capacity and/or storage capacity as a service. "Cloud" may refer to one or more hardware and/or software components that deliver or facilitate the delivery of computing and/or storage capacity, including, but not limited to, one or more of the following: clients, applications, platforms, infrastructure, and/or servers. Cloud may refer to any hardware and/or software associated with clients, applications, platforms, infrastructure, and/or servers. For example, cloud and cloud computing may refer to one or more of the following: computers, processors, storage media, routers, switches, modems, virtual machines (e.g., virtual servers), data centers, operating systems, middleware, firmware, hardware backends, software backends, and/or software applications. Cloud may refer to private, public, hybrid, and/or community clouds. A cloud may be a shared pool of configurable computing resources; it may also be public, private, semi-private, distributed, scalable, flexible, temporary, virtual, and/or physical. Clouds or cloud services may be delivered over one or more types of networks, such as mobile communication networks and the Internet.

As used in this application, cloud or cloud services may include one or more of the following: Infrastructure as a Service (IaaS), Platform as a Service (PaaS), Software as a Service (SaaS), and/or Desktop as a Service (DaaS). As a non-exclusive example, IaaS may include, for example, one or more virtual server instances that can start, stop, access, and/or configure virtual servers and/or storage centers (e.g., providing one or more processors, storage space, and/or network resources on demand, such as EMC and Rackspace). PaaS may include, for example, one or more software and/or development tools hosted on an infrastructure (e.g., a computing platform and/or solution stack from which clients can generate software interfaces and applications (e.g., Microsoft Azure)). SaaS may include, for example, software hosted by a service provider and accessible on a network (e.g., application software and/or data associated with the software application can be maintained on the network, such as Google Apps, SalesForce). DaaS may include, for example, providing desktops, applications, data, and/or services to users on a network (e.g., providing a multi-application framework, applications within the framework, data associated with the application, and/or services associated with the application and/or data on the network (e.g., Citrix)). The foregoing is intended to be exemplary of the various types of systems and/or methods mentioned in this application as "clouds" or "cloud computing" and should not be considered complete or exhaustive.

The proliferation of automation is evident in many transactions. For example, automated teller machines (ATMs) dispense money and accept deposits. Airline ticket counters check passenger check-ins, invoices, and allow passengers to change or renew flights. Train and subway ticket counters allow passengers to purchase tickets to specific destinations without requiring human interaction. Many grocery stores and drug stores have self-service checkout machines that allow consumers to pay for their purchases simply by interacting with the machine. Large companies now have telephone answering systems that have machines that interact with consumers and only involve a human in a transaction if there is a problem with the machine-assisted transaction.

However, as this automation increases, convenience and accessibility may decrease. Self-checkout machines at grocery stores may be difficult to operate. ATMs and ticket counters are often inaccessible to people with disabilities or those who require special access. Previously, human interaction made it relatively easy for people with disabilities to complete transactions, but if a person with a disability cannot press the button on the ATM, the machine cannot facilitate the transaction. Although some of these public terminals allow speech operation, they are configured for the most general form of speech and are less useful for identifying specific speakers, resulting in frustration for users who try to speak to the machine. This problem is particularly challenging for people with disabilities, who already face significant challenges completing transactions through automated machines.

In addition, smartphones and tablet devices are now also configured to receive spoken commands. Automotive systems controlled by speech and voice are now common in motor vehicles, even in economical, mass-produced vehicles. Home entertainment devices (such as disc players, televisions, radios, stereos, etc.) can respond to spoken commands. In addition, home security systems can respond to spoken commands. In office settings, workers' computers can respond to speeches from workers to allow faster and more efficient workflows. These systems and machines can be trained to work for specific users, either through explicit training or through repeated interactions. However, when the system is updated or replaced (such as when buying a new television), the training may be lost along with the equipment. Therefore, in some embodiments described herein, the adaptation data for the speech recognition system may be separated from the equipment that recognizes speech and may be more closely associated with the user, such as through a device carried by the user or through a network location associated with the user.

In addition, in some environments, more than one device may send and receive data within the scope of interaction with the user. For example, simply sitting on a sofa watching TV may involve five or more devices, such as a television, a set-top box and an audio/video receiver, a remote control, and a smart phone device. Some of these devices may send or receive speech data. Some of these devices may send, receive, or store adaptation data, as described in more detail herein. Therefore, in some embodiments (which will be described in more detail herein), there may be some methods, systems, and devices for determining which devices in a system should perform actions that allow the user to effectively interact with the desired device through the user's speech.

Referring now to FIG. 1 (e.g., FIG. 1A ), FIG. 1A illustrates an example environment 100 in which methods, systems, circuits, articles of manufacture, computer program products, and architectures according to various embodiments may be implemented by one or more of the following: personal device 20A, personal device 20B, intermediary device 40, target device 30A, and target device 30B. In some embodiments, such as shown in FIG. 1B , personal device 120, which in some embodiments may be an example of one of personal device 20A, personal device 20B, and intermediary device 40, may be provided. In various embodiments, personal device 120 may be provided with: logic configured to manage adaptation data, wherein the adaptation data is associated with at least one aspect of speech by a particular party; logic configured to facilitate transmission of adaptation data to a target device in response to an indication associated with a speech-facilitated transaction with the particular party, wherein the adaptation data is associated with at least one aspect of speech by the particular party; and logic configured to determine whether to update the adaptation data, the determination being based at least in part on the outcome of at least a portion of the speech-facilitated transaction.

Referring again to the exemplary embodiment of FIG. 1A , user 105 can engage in a speech-facilitated transaction via one or more of terminal devices 30A and 30B. In some embodiments, the speech-facilitated transaction can be directed to either terminal device 30A or terminal device 30B. In some embodiments, the user can direct her speech not specifically toward terminal device 30A or terminal device 30B, but toward both, with it being irrelevant which device performs the speech-facilitated transaction. In some embodiments, one of terminal device 30A and terminal device 30B negotiates between themselves to determine which device will perform the speech-facilitated transaction. In some embodiments, one or more of personal device 20A, personal device 20B, and intermediary device 40 can determine which of terminal device 30A and terminal device 30B will perform the speech-facilitated transaction. In some embodiments, one or more of personal device 20A, personal device 20B, and intermediary device 40 can detect one or more of terminal device 30A and terminal device 30B and establish a connection or negotiation with one or more of terminal devices 30A and 30B.

The dotted arrows shown in the environment 100 of Figure 1A are not numbered, but are intended to represent the data flow from one device to another. Some data connections are omitted for simplifying the accompanying drawings, and for example, although there are no arrows, personal device 20A can directly communicate with terminal device 30A and terminal device 30B. Data flow can include one or more adaptation data, speech data that occur in any format, including the original words from the user, adaptation result data, desired target data, target data, etc. The dotted arrows illustrate the contact between one or more of user 105 and personal device 20A, personal device 20B and intermediate device 40.

Although not shown in FIG1A , any or all of the personal devices 20A, 20B, and 40 may communicate, either directly or indirectly, with any or all of the terminal devices 30A and 30B. In some embodiments, these devices communicate with each other via a server 110, which may be local to or remote from any of the devices 20A, 20B, 30A, 30B, and 40. In some embodiments, these devices communicate with each other via one or more communication networks 140, which may be local to or remote from any of the devices 20A, 20B, 30A, 30B, and 40. Although server 110 and communication network 40 are depicted in each of the embodiments in FIG1A and FIG1C-1E , server 110 and communication network 140 are not required and are shown for illustrative purposes only.

Referring again to FIG. 1A , FIG. 1A illustrates a personal device 20A, a personal device 20B, an intermediary device 40, a terminal device 30A, a terminal device 30B, and a server 110. The number of devices shown is for illustrative purposes only. However, in some embodiments, there may be a varying number of personal devices, intermediary devices, terminal devices, servers, and communication networks. In some embodiments, one or more of the personal devices, intermediary devices, terminal devices, servers, and communication networks may be completely omitted.

Referring again to FIG1A , personal devices 20A, 20B are illustrated as being associated with user 105. This association may be weak, for example, they may only be in the same physical proximity. In other embodiments, the association may be one of an owner, a contract between the two parties, information storage, previous use, or other factors. The examples further described herein will provide a non-exhaustive list of examples of the relationship between user 105 and personal device 120 (e.g., personal device 20A or personal device 20B). In some embodiments, personal device 120 (e.g., personal device 20A or personal device 20B) can be any size and have any specifications. Personal device 120 (e.g., personal device 20A or personal device 20B) can be a custom device of any shape or size that is configured to send, receive, and store data. Personal device 120 (e.g., personal device 20A or personal device 20B) may include, but is not limited to, a smartphone device, a tablet device, a personal computer device, a laptop device, a keychain device, a key, a personal digital assistant device, a modified memory stick, a universal remote control, or any other electronic device. In addition, the personal device 120 (e.g., personal device 20A or personal device 20B) can be a modified wearable object, such as glasses, a wallet, a credit card, a watch, a necklace, or a clothing accessory. Anything configured to store, send, and receive data can be a personal device 120 (e.g., personal device 20A or personal device 20B), and the size of the personal device 120 (e.g., personal device 20A or personal device 20B) is not limited to the size of a device that can be carried by the user. In addition, the personal device 120 (e.g., personal device 20A or personal device 20B) may not be directly close to the user. For example, the personal device 120 (e.g., personal device 20A or personal device 20B) can be a computer located on a desk in the user's home or office.

Although the terminal devices 30A, 30B (hereinafter interchangeably referred to collectively or individually as "terminal devices 30*") are described as "terminal devices", this is merely for simplicity of description. The terminal device 30* can be any device configured to receive speech. For example, the terminal device 30* can be a terminal, a computer, a navigation system, a phone, a piece of home electronics (such as a DVD player, a Blu-ray player, a media player, a gaming system, a television, a receiver, an alarm clock, etc.). In some embodiments, the terminal device 30* can be a home security system, a security lock, a door lock, a kitchen appliance, etc. configured to receive speech. In some embodiments, the terminal device 30* can be a motor vehicle, such as a car, a boat, an airplane, a motorcycle, a golf cart, a wheelchair, etc. In some embodiments, the terminal device 30* can be a portable electronic device, such as a laptop computer, a netbook computer, a tablet device, a smart phone, a cellular phone, a radio, a portable navigation system, or any other piece of electronic device capable of receiving speech. The terminal device 30* can be part of an enterprise solution, such as a shared workstation in an office, a copier, a scanner, a personal workstation in a cubicle, an office directory, an interactive screen, and a telephone. These examples and lists are not intended to be exhaustive, but rather to illustrate only a few examples of terminal devices. Some of these examples are shown in greater detail with respect to FIG1C , FIG1D , and FIG1E .

In some embodiments, the target device 30A and/or the target device 30B receives adaptation data from the personal device 120 (e.g., personal device 20A or personal device 20B) in a method described in more detail herein. In some embodiments, the adaptation data is sent over one or more communication networks 40. In various embodiments, the communication network 40 may include one or more of a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a wireless local area network (WLAN), a personal area network (PAN), a World Interoperability for Microwave Access (WiMax), a public switched telephone network (PTSN), a general packet radio service (GPRS) network, a cellular network, and the like. The communication network 40 may be a wired network, a wireless network, or a combination of a wired network and a wireless network. It should be noted that the term "communication network" herein refers to one or more communication networks that may or may not be interoperable with each other.

In some embodiments, the adaptation data does not come directly from the personal device 120 (e.g., personal device 20A or personal device 20B). In some embodiments, the personal device 120 (e.g., personal device 20A or personal device 20B) merely facilitates the communication of the adaptation data, for example, by providing one or more of an address, credentials, instructions, authorization, and a recommendation. For example, in some embodiments, the personal device 120 (e.g., personal device 20A or personal device 20B) provides a location on the server 10 where the adaptation data can be received. In some embodiments, the personal device 120 (e.g., personal device 20A or personal device 20B) retrieves the adaptation data from the server 10 upon a request from the terminal device 30 and then relays the adaptation data to the terminal device 30 or facilitates the relay of the adaptation data.

In some embodiments, personal device 120 (e.g., personal device 20A or personal device 20B) broadcasts adaptation data, for example, at predetermined, regular, or otherwise defined intervals, regardless of whether or not end device 30 is listening. In other embodiments, personal device 120 (e.g., personal device 20A or personal device 20B) listens for a request from end device 30 and transmits or broadcasts adaptation data in response to the request. In some embodiments, user 5 determines when personal device 120 (e.g., personal device 20A or personal device 20B) broadcasts adaptation data. In still other embodiments, a third party (not shown) triggers the transmission of adaptation data to end device 30, where the transmission is facilitated by personal device 120 (e.g., personal device 20A or personal device 20B).

FIG1B shows a more detailed description of a personal device 120 in the exemplary environment 100. The personal device 120 may be an example of the personal device 20A or 20B of FIG1A , the intermediate device 40 of FIG1A , the first personal device 21A of FIG1C , the second personal device 21B of FIG1D , one of the modules of the device 31 of FIG1C , the personal device 22A of FIG1D , the personal device 22B of FIG1D , any of the devices 51 , 52 , 53 , and 54 of FIG1D , the smart key device 26 of FIG1E , the GPS navigation device 41 of FIG1E , etc. The foregoing is not intended to be an exhaustive description of possible devices corresponding to the personal device 120 of FIG1B , but rather is merely an example of the types of devices that may have the structure outlined in FIG1B .

1B , in various embodiments, personal device 120 may include, among other things, a processor 132, a memory 134, a user interface 135, a speech detection interface 138, and a data transmission interface 137. Each of these components may not be present in various embodiments of personal device 120; for example, some personal devices 120 may not have speech detection interface 138, memory 134, or user interface 135.

Processor 132 may include one or more microprocessors, central processing units (CPUs), graphics processing units (GPUs), physical processing units, digital signal processors, network processors, floating-point processors, and the like. In some embodiments, processor 132 may be a server. In some embodiments, processor 132 may be a distributed core processor. Although processor 132 is a single processor as part of a single personal device 120, processor 132 may be multiple processors distributed across one or more computing devices 30, which may or may not be configured to work together. Processor 132 is illustrated as being configured to execute computer-readable instructions to perform one or more operations as previously described and illustrated in Figures 5, 6A-6B, 7A-7D, and 8A-8I. In some embodiments, processor 132 is designed and configured to operate as processing module 150, which may include one or more of the following: a speech adaptation data conditioning module 152 associated with at least one aspect of a particular party, a facilitation module 154 for transmitting speech adaptation data in response to an indication of a speech-facilitated transaction involving a target device, and a module 156 for determining possible revisions to the speech adaptation data based in part on the results of the speech-facilitated portion.

Referring again to FIG. 1B , as previously described, personal device 120 may include memory 134. In some embodiments, memory 134 may include one or more of the following: one or more mass storage devices; read-only memory (ROM); programmable read-only memory (PROM); erasable programmable read-only memory (EPROM); cache memory such as random access memory (RAM), flash memory, synchronous random access memory (SRAM), dynamic random access memory (DRAM); and/or other types of storage devices. In some embodiments, memory 134 may be located at a single network location. In some embodiments, memory 134 may be located at multiple network locations, including locations that are remote from one another.

Referring again to FIG1B , as previously described, personal device 120 may include a user interface 135. The user interface may be implemented in hardware, software, or both, and may include various input and output devices to allow an operator of personal device 120 to interact with personal device 120. For example, user interface 135 may include, but is not limited to: an audio display (e.g., speaker 108); a video display (e.g., screen 102); a microphone; a camera; a keyboard (e.g., keyboard 103); a trackball (e.g., trackball 104); a mouse (e.g., mouse 105); one or more soft keys (e.g., hard/soft keys 106); a touch input (e.g., touch screen 107, which may also be a video display screen); a joystick; a game controller; a touch pad; an earpiece; or any other device that allows interaction between the device and a user.

Referring again to Figure 1B, as previously described, the personal device 120 may include a speech detection interface 138. The speech detection interface 138 may be configured to receive and/or process speech as input or to observe and/or record speech for speech-facilitating transactions. Although not present in some embodiments, in some embodiments, the speech detection interface 138 may include a speech indication receiver 112, which may be any type of sensor, or a communication port that receives a signal, or a sensor that detects a button press, or any other module capable of detecting any type of change of state in the environment 100 (whether internal or external to the device). The speech detection interface 138 may, in some embodiments, include a microphone 110, which may or may not be in communication with the speech indication receiver 112. In some embodiments, the microphone 110 may be enabled to detect speech, either selectively or constantly, and may be controlled by one or more of the speech indication receiver 112 and the processor 132.

Referring again to FIG. 1B , as previously described, the personal device 120 may include a data transmission interface 137. In some embodiments, the data transmission interface 137 may handle the transmission and reception of data through the device. For example, in some embodiments, the data transmission interface 137 may include an adaptive data transmitter/receiver 114 that handles the transmission and reception of adaptive data over any type of network or internal form of communication (e.g., an internal bus, etc.). In some embodiments, the data transmission interface 137 may include a speech data transmitter/receiver 116 that handles the transmission and reception of speech data (including original speech) over any form of mobile data.

Referring again to FIG. 1B , as previously described, personal device 120 may include one or more sensors 182 . These sensors include, but are not limited to, a global positioning system (GPS) sensor; a still camera; a video camera; an altimeter; an air quality sensor; a barometer; an accelerometer; a charge-coupled device (CCD); a radio; a thermometer; a pedometer; a heart rate monitor; a moisture sensor; a humidity sensor; a microphone; a seismometer; and a magnetic field sensor. Sensor 182 may be connected to sensor interface 180 . Although FIG. 1B illustrates sensor 182 as part of personal device 120 , in some embodiments, sensor 182 may be separate from personal device 120 and communicate via one or more communication networks (e.g., communication network 140 ).

Referring now to FIG. 1C , FIG. 1C illustrates an exemplary embodiment of an exemplary environment 100′, which is a non-limiting example of environment 100. As shown in FIG. 1C , environment 100′ may include a user (not shown), who may have one or more of a first personal device 21A and a second personal device 21B. While both personal device 21A and personal device 21B may be any of the personal devices 120 described above, first personal device 21A may be, for example, a USB drive, while second personal device 21B may be, for example, a cellular phone. One or more of first personal device 21A and second personal device 21B may interact with device 31, which may be any type of computing device, such as a laptop, desktop computer, server, netbook, tablet device, smartphone, or the like. Device 31 may have operating system software 81 loaded thereon. Operating system software 81 may include, but is not limited to, Microsoft Windows, Google Android, Apple iOS, Apple Mountain Lion, UNIX, Linux, Chrome OS, Symbian, and the like.

Additionally, in some embodiments, the device 31 may include onboard enterprise client software 82. For example, some systems (e.g., in an office environment) may have client software (e.g., Citrix, etc.) loaded onto their systems to integrate the user experience of their workers. In some embodiments, this module may function to determine the interpretation of speech data (e.g., speech data 101) and the role of the application that adapts the data. In some embodiments, the device 31 may also include one or more of a first application software 91 and a second application software 92. The first and second application software 91, 92 may be any type of application, such as a game, a spreadsheet, a word processor, a web browser, a chat client, a picture viewer, a picture manipulator, a webcam application, and the like. In some embodiments, these modules may function to determine the interpretation of speech data and the role of the application that adapts the data. For example, the complexity of the application may function to determine how much speech processing occurs at the application layer. In some embodiments, the device 31 may communicate with one or more communication networks 140 and one or more servers 110.

Referring now to FIGURE 1D, FIGURE 1D illustrates an exemplary embodiment of exemplary environment 100", which is a non-limiting example of environment 100. As shown in FIGURE 1D, environment 100" may include user 105, who may have one or more of personal device 22A and personal device 22B. Although both personal device 22A and personal device 22B may be any form of personal device 120 as previously described, personal device 22A may be, for example, a universal remote control and personal device 22B may be, for example, a cellular telephone device. In some embodiments, one or both of personal device 22A, personal device 22B, and computing device 54 may send, store, and/or receive adaptation data. In some embodiments, one of personal device 22A, personal device 22B, and computing device 54 may determine which device shown in FIGURE 1D the user 105 is speaking toward. In other embodiments, one or more of the receiver device 51, the media player device 52, and the television device 53 may send one or more of speech data and adaptation data back and forth, and one or more of the receiver device 51, the media player device 52, and the television device 53 may determine which device of the devices 22A, 22B, 51, 52, 53, and 54 should apply the adaptation data and which device should process the speech data.

Now referring to Figure 1E, Figure 1E shows an exemplary embodiment of an exemplary environment 100'", which is a non-limiting example of environment 100. As shown in Figure 1E, environment 100' may include a user (not shown) driving a car (only the interior of the car is shown), wherein the car is equipped with a motor vehicle control system 42, which can control non-driving features of the car, such as music, climate, temperature, fuel management, seat position, media playback, lighting, etc. The car may also have a smart key device 26, which in some embodiments can store, receive and/or send adaptation data, either wirelessly or through the car's system. In some embodiments, environment 100' may also include a GPS navigation device 41, which can be an example of an intermediate device 40, which can also be a personal device 120. In some embodiments, the GPS navigation device 41 can act as a terminal device that receives speech data and adaptation data to process the user's request. In other embodiments, the GPS navigation device 41 may function as the personal device 120, storing adaptation data derived from the user's navigation commands and transmitting the adaptation data to the target device (e.g., the vehicle control system 42) when necessary. For example, the intermediate device 40 shown in FIG. 1A , and the GPS navigation device 41, which may be an example of the intermediate device 40, may be the personal device 120 used in the first transaction and the terminal device in the second transaction. In some embodiments, the GPS navigation device 41 may change its role based on analysis of data received by the GPS navigation device 41.

1E , in some embodiments, the GPS navigation device 41, the motor vehicle control system 42, the smart key device 26, and the user's personal device (not shown) may communicate with one or more communication networks 140 and one or more servers 110. However, as in all of the illustrated exemplary embodiments, these elements are optional and some embodiments may exclude them.

Referring now to FIG2 , FIG2 illustrates an exemplary implementation of a speech adaptation data conditioning module 152 associated with at least one aspect of a particular party. As shown in FIG2 , the speech adaptation data conditioning module 152 associated with at least one aspect of a particular party may include one or more sub-logic modules in various alternative implementations and embodiments. For example, as shown in FIG2 (e.g., FIG2A ), in some embodiments, the module 152 may include one or more of the following: a speech adaptation data conditioning module 202 associated with at least one prior interaction between a particular party and a device; a module 204 for obtaining an address for storing speech adaptation data; a module 206 for determining whether speech adaptation data is available at the obtained address at a particular time; a speech adaptation data obtaining module 208 associated with at least one aspect of a particular party; a speech adaptation data monitoring module 210 associated with at least one aspect of a particular party access; an adaptation data conditioning module 212 for associating pronunciation of one or more syllables with speech of one or more concepts; an adaptation data address generating module 214; and an adaptation data address providing module 216.

2, such as FIG. 2B, in some embodiments, the module 152 may include one or more of the following: a module 218 for generating an address of the adaptation data and a module 220 for providing the address of the adaptation data upon request.

Referring now to FIG3 , FIG3 illustrates an exemplary implementation of a speech-adaptive data transmission facilitation module 154 responsive to an indication of a speech-facilitated transaction with a target device. As shown in FIG3 , the speech-adaptive data transmission facilitation module 154 responsive to an indication of a speech-facilitated transaction with a target device may include one or more sub-logic modules in various alternative implementations and embodiments. For example, as shown in FIG3 (e.g., FIG3A ), in some embodiments, module 154 may include one or more of the following: a speech-adaptive data facilitation module 302 responsive to an indication of a speech-facilitated transaction with a target device, including a list of one or more words and corresponding pronunciations; a speech-adaptive data facilitation module 304 responsive to an indication of a speech-facilitated transaction with a target device, including a transmission of instructions for modifying a word frequency table; a speech-adaptive data facilitation module 306 responsive to an indication of a speech-facilitated transaction with a target device, including a transmission of a word completion algorithm; and a speech-adaptive data transmission facilitation module 308 responsive to an indication of an intent to perform a speech-facilitated transaction. In some embodiments, module 308 may include a facilitation module 310 for transmitting adaptation data responsive to receiving an indication of an intent to perform a speech-facilitated transaction from a target device. In some embodiments, module 310 may include one or more of the following: a speech-adapted data transmission facilitation module 312 in response to receiving an indication from a target device that a particular party is interacting with an input portion of the target device; a speech-adapted data transmission facilitation module 314 in response to receiving an indication that a particular party is speaking toward the target device; and a speech-adapted data transmission facilitation module 316 in response to a request for speech adaptation data.

3, such as FIG3B, modules 154 may include module 308 as previously described. In some embodiments, module 308 may include a speech-adapted data transfer facilitation module 318 responsive to an indication of intent to perform a speech-facilitated transaction received from a particular device.

Referring again to FIG. 3 , for example, FIG. 3C , module 154 may include one or more of the following: sending first speech adaptation data associated with a first aspect of the particular party's speech to target device module 320 and sending second speech adaptation data associated with a second aspect of the particular party's speech to target device module 322. In some embodiments, module 320 may include one or more of the following: sending first speech adaptation data associated with the particular party's speech style to target device module 324 and sending first speech adaptation data associated with expected vocabulary to target device module 326. In some embodiments, module 326 may include sending first speech adaptation data associated with vocabulary estimated to be used during a speech-facilitated transaction to target device module 328. In some embodiments, module 328 may include one or more of the following: sending first speech adaptation data associated with one or more food terms estimated to be used during a speech-facilitated transaction to target device module 330; and sending first speech adaptation data associated with one or more electronic devices estimated to be used during a speech-facilitated transaction to target device module 332. In some embodiments, module 322 may include sending second speech adaptation data associated with the second aspect of the particular party's speech to target device module 340 in response to a request from the target device.

Referring again to FIG. 3 , for example, FIG. 3D , module 154 may include one or more of modules 320 and 322 as described above. In some embodiments, module 320 may include one or more of the following: first speech adaptation data associated with the spoken language is sent to a target device module 334, and first speech adaptation data associated with previous speech-facilitated transactions by a group of members having a particular property is sent to a target device module 336. In some embodiments, module 336 may include sending first speech adaptation data associated with previous speech-facilitated transactions by a group of members from a particular community to a target device module 338. In some embodiments, module 322 may include one or more of the following: second speech adaptation data associated with a second aspect different from the first aspect is sent to a target device module 342. In some embodiments, module 342 may include sending second speech adaptation data associated with a second set of previous speech interactions to a target device module 344, the second set of previous speech interactions being different from the first set associated with the first speech adaptation data. In some embodiments, module 344 may include sending second speech adaptation data associated with a second set of previous speech interactions that is smaller than the first set associated with the first speech adaptation data to a target device module 346.

Referring now to Figure 4, an exemplary implementation of a module 156 for determining possible revisions to speech adaptation data based in part on the results of a portion of a speech-facilitated transaction is shown. As shown in Figure 4, the module 156 for determining possible revisions to speech adaptation data based in part on the results of a portion of a speech-facilitated transaction may include one or more sub-logic modules in various alternative implementations and embodiments. For example, as shown in Figure 4 (e.g., Figure 4A), in some embodiments, module 156 may include one or more of the following: a module 402 for modifying speech adaptation data based in part on the results of a portion of a speech-facilitating transaction; a module 404 for determining speech adaptation data relative to the modified data based in part on the results of a portion of a speech-facilitating transaction; a module 406 for determining possible modifications to speech adaptation data based in part on the results of an initial portion of a speech-facilitating transaction; a module 408 for determining possible modifications to speech adaptation data based in part on the results of an initial portion of a speech-facilitating transaction; a module 410 for determining possible modifications to speech adaptation data based in part on a first sentence of a speech-facilitating transaction that occurs before a second sentence of the speech-facilitating transaction; a module 412 for determining possible modifications to speech adaptation data based in part on the results of a portion of a speech-facilitating transaction and made before the speech-facilitating transaction ends; and a module 414 for determining possible modifications to speech adaptation data based in part on the results of a portion of a speech-facilitating transaction after at least one word is spoken by a particular party. In some embodiments, module 414 may include module 416 for determining possible corrections to the utterance adaptation data based in part on the results of a portion of a transaction that facilitated the utterance and that preceded a particular word.

Referring again to FIG. 4 , for example, FIG. 4B , module 156 may include one or more of the following: a speech-facilitated transaction result acquisition module 418; and a module 420 for determining possible corrections based in part on speech adaptation data of the acquired results. In some embodiments, module 418 may include one or more of the following: a module 422 for acquiring a speech-facilitated transaction result portion from a target device; a module 424 for acquiring a speech-facilitated transaction result portion from a specific party; and a module 432 for indicating that no transaction acquisition was fully successful (which, in some embodiments, may include, for example, a speech-facilitated transaction result portion indicating an incomplete or low-confidence interpretation of the transaction acquisition portion). In some embodiments, module 424 may include one or more of the following: a module 426 for acquiring a speech-facilitated transaction result portion from a specific device operated by a specific party (which, in some embodiments, may include, for example, a speech-facilitated transaction result portion acquired at least in part as a result of a button press on the specific device) and a module 430 for acquiring a speech-facilitated transaction feedback portion from a specific device operated by a specific party.

Referring again to FIG. 4 , for example, FIG. 4C , module 156 may include one or more of modules 418 and 420 as described above. In some embodiments, module 418 may include one or more of the following: a module 436 for obtaining a speech-facilitated transaction result portion indicating that the target device failed to perform at least a portion of the speech-facilitated transaction; a module 442 for obtaining a speech-facilitated transaction result portion from a particular party via the target device; a module 444 for obtaining a speech-facilitated transaction result portion including one or more interpreted words; a module 446 for obtaining a speech-facilitated transaction result portion including one or more incompletely interpreted words; and a module 448 for obtaining a speech-facilitated transaction result portion including a representation of the particular party speaking one or more words of the speech-facilitated transaction. In some embodiments, module 436 may include one or more of the following: a module 438 for obtaining a speech-facilitated transaction result portion indicating that an error rate determined by the target device is above a threshold; and a module 440 for obtaining a speech-facilitated transaction result portion indicating that a confidence rate determined by the target device is below a threshold.

4, for example, FIG4D, modules 156 may include one or more of modules 418 and 420 as described above. In some embodiments, module 418 may include one or more of the following: a module 450 for acquiring a speech-facilitated transaction result portion including a representation of a target device that interprets one or more words of a speech-facilitated transaction, and a module 452 for acquiring a speech-facilitated transaction result portion including a data structure configured to store one or more interpreted words of a speech-facilitated transaction and one or more corresponding representations of pronunciations of the one or more interpreted words. In some embodiments, module 156 may include one or more of the following: a module 454 for receiving at least a portion of the results of the speech-facilitating portion of the transaction; a module 456 for correcting the speech adaptation data based at least in part on at least a portion of the received results; a module 458 for sending updated speech adaptation data before completing the speech-facilitating transaction; a module 460 for receiving the results of the speech-facilitating portion of the transaction; a module 462 for correcting the speech adaptation data based in part on the results; a module 464 for obtaining at least a portion of the results of the speech-facilitating portion of the transaction; a module 466 for adjusting the speech adaptation data based at least in part on at least a portion of the received results; and a module 468 for sending a signal indicating adaptation of the speech adaptation data.

Referring again to Figure 4, for example Figure 4E, module 156 may include one or more of the following: a module 470 for receiving possible correction data from a further device; a module 472 for applying possible correction data received from a further device to the speech adaptation data; a module 474 for receiving a speech-facilitating transaction result portion; a module 476 for sending the speech-facilitating transaction result portion to the device (which in some embodiments may include a module 480 for sending the speech-facilitating transaction result portion to a device storing the speech adaptation data); a module 478 for indicating whether to correct the speech adaptation data received from the device (which in some embodiments may include a module 482 for indicating how to correct the speech adaptation data received from the device); a module 484 for receiving a speech-facilitating transaction result portion; a module 486 for making a speech adaptation data correction decision based in part on the speech-facilitating transaction result portion; a module 488 for requesting correction of the speech adaptation data sent to the device; and a module 490 for obtaining the corrected adaptation data from the device.

Referring again to FIG. 4 , for example, FIG. 4F , module 156 may include one or more of the following: a module 492 for acquiring results for a particular portion of a speech-facilitated transaction; a module 494 for applying possible corrections to speech adaptation data based at least in part on the acquired results for the particular portion of a speech-facilitated transaction; and a module 496 for transmitting the corrected speech adaptation data to another portion of the speech-facilitated transaction via a target device. In some embodiments, module 494 may include a module 498 for applying an algorithm for possible corrections to speech adaptation data based at least in part on the acquired results for the particular portion of a speech-facilitated transaction. In some embodiments, module 498 may include one or more of the following: a module 401 for applying parameters of an algorithm for possible corrections to speech adaptation data based at least in part on the acquired results for the particular portion of a speech-facilitated transaction; and a module 403 for selecting different algorithms for speech adaptation data based at least in part on the acquired results for the particular portion of a speech-facilitated transaction.

Referring again to FIG. 4 , for example, FIG. 4G , module 156 may include one or more of modules 492, 494, and 496 as described above. In some embodiments, module 494 may include module 405 for applying possible revisions to the pronunciation dictionary based at least in part on the results obtained for the specific portion of the transaction that facilitates speech. In some embodiments, module 405 may include one or more of the following: module 407 for adding one or more words to the pronunciation dictionary based at least in part on the results obtained for the specific portion of the transaction that facilitates speech; module 409 for adding one or more words to the pronunciation dictionary that includes the one or more words based at least in part on the results obtained for the specific portion of the transaction that facilitates speech; and module 411 for replacing the pronunciation dictionary based at least in part on the results obtained for the specific portion of the transaction that facilitates speech.

Referring again to FIG. 4 , for example, FIG. 4H , module 156 may include one or more of modules 492, 494, and 496 as previously described. In some embodiments, module 494 may include module 413 for applying a path selection algorithm to a possible modified path based at least in part on the results of obtaining the specific portion of the speech-favored transaction. In some embodiments, module 496 may include one or more of the following: a module 415 configured to transmit modified speech adaptation data for interpreting another portion of the speech-favored transaction; a module 417 configured to transmit modified speech adaptation data for interpreting another portion of the speech-favored transaction directly after interpreting the specific portion; a module 419 for transmitting modified speech adaptation data; and a module 421 for receiving an indication of the modified speech adaptation data.

Referring again to FIG. 4 , for example, FIG. 4I , module 156 may include one or more of modules 492, 494, and 496 as previously described. In some embodiments, module 496 may include one or more of the following: a module 423 for sending modified speech adaptation data; a module 425 for receiving an indication that the modified speech adaptation data applies; and a module 427 for facilitating an indication that a further portion of the speech-facilitated transaction is ready for completion. In some embodiments, module 427 may include one or more of the following: a module 429 for displaying a message indicating that a further portion of the speech-facilitated transaction is ready; and a module 431 for facilitating a message on a target device indicating that a further portion of the speech-facilitated transaction is ready for completion.

Below is a series of flow charts describing the implementation. For ease of understanding, these flow charts are organized so that the initial flow chart represents the implementation via an exemplary implementation, and subsequent flow charts represent alternative implementations and/or extensions of the initial flow chart, either as sub-component operations or as additional component operations built on one or more previously given flow charts. It will be understood by those skilled in the art that the representations utilized herein (e.g., initially providing a flow chart representation of an exemplary implementation and subsequently providing additional content and/or further details to subsequent flow charts) generally allow for quick and easy understanding of the implementations of each process. Additionally, it will be further understood by those skilled in the art that the representations used herein lend themselves well to module-oriented and/or object-oriented programming paradigms.

In addition, in Figures 2-4 and subsequent figures, various operations may be depicted in a box-within-a-box format. This depiction may indicate that the operations within the inner box may include optional exemplary embodiments of the operational steps shown in one or more outer boxes. However, it should be understood that the inner box operations may be considered independent operations separated from any associated outer boxes and may be performed in any order relative to all other illustrated operations, or may be performed simultaneously. Furthermore, these operations shown in Figures 5-8 and other operations described herein may be performed by at least one of a machine, an article, or a combination of materials.

Referring now to FIG5 , FIG5 illustrates operations 500, which may include operations 502 describing managing adaptation data associated with at least one aspect of speech by a particular party. For example, FIG1 (e.g., FIG1B ) illustrates a conditioning module 152 managing (e.g., storing, tracking, monitoring, authorizing, changing permissions, providing access to, allocating storage for, retrieving, receiving, processing, altering, comparing, or otherwise performing one or more operations on) adaptation data associated with at least one aspect of speech by a particular party, wherein adaptation data (e.g., a phrase completion algorithm used to help interpret spoken words based on context) is associated with at least one aspect of speech by a particular party (e.g., a user previously performing speech-facilitated transactions through different automated teller machine (ATM) terminals, and multiple groups of words spoken by the user help form contextual rules used by at least a portion of the phrase completion algorithm).

Referring again to FIG. 5 , operations 500 may include operation 504 depicting facilitating sending adaptation data to a target device in response to an indication associated with the speech-facilitated transaction for the particular party, wherein the adaptation data is associated with at least one aspect of speech by the particular party. For example, Figure 1 (e.g., Figure 1B) shows a facilitation module 154 that transmits speech adaptation data in response to an indication of a speech-enabled transaction involving a target device, the facilitation module 154 facilitating the transmission (e.g., sending, or taking one or more steps that facilitate transmission, regardless of the starting or ending point) of adaptation data (e.g., a phrase completion algorithm that assists in interpreting spoken words based on context) to a target device in response to an indication of a speech-enabled transaction (e.g., at least a portion of the transaction being instructing an ATM to withdraw two hundred dollars from an ATM device terminal using a speech command) by a particular party (e.g., a user of an ATM device), such as the user either standing in front of the ATM device terminal, or inserting her card, or pressing a button, or speaking a starting phrase displayed on a screen of the ATM terminal, wherein the adaptation data is associated with at least one aspect of the speech of the particular party (e.g., the user previously performed speech-enabled transactions through different ATM device terminals, and multiple groups of words spoken by the user helped form contextual rules that were used by at least a portion of the phrase completion algorithm).

Referring again to Figure 5, operation 500 may include operation 506, which depicts determining whether to update adaptation data, the determination being based at least in part on the results of at least a portion of the speech-enabled transaction. For example, Figure 1 (e.g., Figure 1B) illustrates module 156 for determining a possible revision of speech adaptation data based in part on the results of a portion of the speech-enabled transaction, the module 156 determining whether to update (e.g., change, modify, change its timestamp, change its parameters, delete, append, alter, send to a different location, change its address, regenerate, or otherwise manipulate) adaptation data (e.g., a phrase completion algorithm used to assist in interpreting spoken words based on context), the determination being based at least in part on the results (e.g., represented numerically or otherwise, provided by machine reasoning, explicit user input, or other source, with or without human intervention) of at least a portion of the speech-enabled transaction (e.g., instructing an ATM to withdraw two hundred dollars from an ATM device terminal using a speech command for at least a portion of the transaction).

Figures 6A-6B depict various implementations of operation 502 according to embodiments. Referring now to Figure 6A, operation 502 may include an operation 602 depicting managing adaptation data, wherein the adaptation data is associated with at least one prior speech-facilitated transaction made by a particular party. For example, Figure 2 (e.g., Figure 2A) illustrates a speech adaptation data conditioning module 202 associated with at least one prior interaction between a particular party and a device, the module 202 managing adaptation data (e.g., an ungrammatical utterance removal algorithm), wherein the adaptation data is associated with at least one prior speech-facilitated transaction made by the particular party (e.g., ungrammatical utterances of a user in a prior transaction were recorded and analyzed and stored in the adaptation data so that they can be more effectively removed in future speech-facilitated transactions).

6A , operation 502 may include operation 604, which depicts obtaining a reference to the location of the adaptation data. For example, FIG. 2 (e.g., FIG. 2A ) shows an obtaining module 204 where the address of the speech adaptation data is stored, the obtaining module 204 obtaining (e.g., receiving, acquiring, generating, retrieving, creating, or otherwise obtaining) a reference to the computer location (e.g., Internet Protocol “IP”) address where the adaptation data (e.g., a portion of the pattern tree model) is stored (adaptation data).

6A , operation 502 may include operation 606, which depicts testing the availability of adaptation data at the location specified by the stored reference. For example, FIG. 2 (e.g., FIG. 2A ) illustrates module 206 for determining whether speech adaptation data is available at the obtained address at a particular time, which tests the availability of adaptation data at the location specified by the stored reference (IP address) (e.g., at the device specified by the IP address) (e.g., determining whether a network connection is available to retrieve the adaptation data, or checking the file integrity of the adaptation data).

Referring again to FIG6A , operation 502 may include operation 608, which depicts obtaining adaptation data, wherein the adaptation data is based at least in part on at least one speech interaction of the particular party. For example, FIG2 (e.g., FIG2A ) illustrates a module 208 for obtaining speech adaptation data associated with at least one aspect of the particular party, wherein the module 208 obtains adaptation data (e.g., a regional dialect application algorithm), wherein the adaptation data is based at least in part on at least one speech interaction of the particular party (e.g., a user running a program on a home computer that records the user's speech and trains the system, the system learning the user's regional dialect through the training program and generating or revising the regional dialect application algorithm).

6A , operation 502 may include operation 610, which depicts controlling access to adaptation data, wherein the adaptation data is based at least in part on at least one speech interaction of a particular party. For example, FIG. 2 (e.g., FIG. 2A ) illustrates a monitoring module 210 for speech adaptation data associated with at least one aspect of access by a particular party, the monitoring module 210 controlling access (e.g., maintaining a permission list, or determining one or more users/programs/devices/etc. that are allowed to read, modify, update, and/or delete) to the adaptation data (e.g., a random state transition network), wherein the adaptation data is based at least in part on at least one speech interaction of a particular party (e.g., a user giving a speech command to a speech-enabled Blu-ray player).

6A , operation 502 may include operation 612, which describes managing adaptation data, the adaptation data including data linking the pronunciation of one or more phonemes made by a particular party to one or more concepts. For example, FIG2 (e.g., FIG2A ) illustrates a conditioning module 212 for speech adaptation data linking the pronunciation of one or more syllables to one or more concepts, the conditioning module 212 managing adaptation data including data linking the pronunciation of one or more phonemes (e.g., phonemes comprising the word “twenty” made by a particular party) to one or more concepts (e.g., a concept having some “twenty,” such as withdrawing twenty dollars if the device communicating therewith is an automated teller machine device).

6A , operation 502 may include operation 614, which depicts obtaining a reference for the location of the adaptation data. For example, FIG. 2 (e.g., FIG. 2A ) illustrates the adaptation data address generation module 214, which obtains (e.g., retrieves from memory) a reference for the location of the adaptation data (e.g., a phrase completion algorithm) (e.g., a location in a cloud service (e.g., Amazon's cloud service)).

6A , operation 502 may include operation 616, which depicts providing the location of the adaptation data at specific intervals. For example, FIG. 2 (e.g., FIG. 2A ) illustrates the providing module 216 of the adaptation data address, which provides (e.g., generally broadcasts or sends to specific one or more devices) the location of the adaptation data (e.g., a phrase completion algorithm) at specific intervals (e.g., once per minute).

6B , operation 502 may include operation 618, which describes obtaining a reference to a location of adaptation data. For example, FIG. 2 (e.g., FIG. 2B ) illustrates an adaptation data address generation module 218 that obtains (e.g., receives from a remote source, such as a remote server) a reference to a location (e.g., a web address or a networked drive) of adaptation data (e.g., a basic pronunciation adjustment algorithm).

6B , operation 502 may include operation 620, which depicts providing the location of adaptation data upon request. For example, FIG2 (e.g., FIG2B ) illustrates module 220 for providing the address of adaptation data upon request, which module 220 provides the location (e.g., a directory and file name on a network drive) of adaptation data (e.g., a base pronunciation adjustment algorithm) upon request (e.g., upon receiving a request from a user of the device or from a signal received from another device (e.g., a target device such as a speech-enabled digital video disc (DVD) player).

6B , operation 502 may include operation 622, which depicts managing a ranked list of spoken languages, wherein the ranked list of spoken languages corresponds to languages understood by the particular party and is ranked by preference. For example, FIG2 (e.g., FIG2B ) illustrates a conditioning module 222 for a list of languages spoken by a particular party, the conditioning module 222 managing a ranked list of spoken languages (e.g., “English, French, Spanish, Italian, German”), wherein the ranked list of spoken languages corresponds to languages understood by the particular party (e.g., a user may speak English as a first language, be fluent in French, understand Spanish, and be able to recognize a small vocabulary in Italian and German) and is ranked by preference (e.g., a user prefers to speak English, then French, then other languages).

Referring again to FIG. 6B , operation 502 may include operation 624 depicting managing a ranked list of spoken languages, wherein the ranked list of spoken languages corresponds to languages understood by a particular party and is ranked by preference, and the ranked list of spoken languages is configured to be received by a device configured to generate a preferred language based in part on the ranked list of spoken languages and in part on a device list of spoken languages understood by the device. For example, Figure 2 (e.g., Figure 2B) shows an adjustment module 224 for a list of languages spoken by a particular party and configured to facilitate the selection of a language for transaction communications, which adjustment module 224 manages a ranked list of spoken languages (e.g., English, Spanish, and French), where the ranked list of spoken languages corresponds to languages understood by the particular party and ranked by preferences, and the ranked list of spoken languages is configured to be received by a device (e.g., an automatic ticket vending machine in a Spanish airport), which is configured to generate a preferred language (e.g., Spanish) based in part on the ranked list of spoken languages (e.g., English, Spanish, and French) and in part on a device list of spoken languages understood by the device (e.g., Spanish, Basque, Italian, and French), thereby selecting Spanish as a common option for both lists and with a higher "rank" than French.

Figures 7A-7B illustrate various implementations of operation 504 according to embodiments. Referring now to Figure 7A , operation 504 may include operation 702, which depicts transmitting a pronunciation dictionary to a target device in response to an indication associated with a speech-facilitated transaction with a particular party, wherein adaptation data is associated with at least one aspect of speech of the particular party. For example, Figure 3 (e.g., Figure 3A ) illustrates a facilitation module 302 transmitting speech adaptation data including a list of one or more words and corresponding pronunciations in response to an indication of a speech-facilitated transaction with a particular party (e.g., a user pressing a button on a steering wheel indicating that the user wishes to give a speech command), transmitting a pronunciation dictionary to a target device (e.g., a motor vehicle control system) in response to an indication associated with a speech-facilitated transaction with a particular party (e.g., a user pressing a button on a steering wheel indicating that the user wishes to give a speech command), wherein adaptation data (e.g., an utterance ignoring algorithm) is associated with at least one aspect of speech of the particular party (e.g., associated with a previous pronunciation of a word spoken by the user).

Referring again to FIG7A , operation 504 may include operation 704 depicting sending a set of instructions to a target device for replacing a word frequency table with a revised word frequency table reflecting the specific party's usage of words in response to an indication of a speech-facilitated transaction associated with a particular party, wherein the adaptation data is associated with at least one aspect of the specific party's speech. For example, FIG3 (e.g., FIG3A ) illustrates a speech adaptation data transmission facilitation module 304 including instructions for revising the word frequency table in response to an indication of a speech-facilitated transaction associated with a particular party (e.g., a user of a speech-enabled personal media player), sending a set of instructions to a target device (e.g., a speech-enabled personal media player) for replacing a word frequency table with a revised word frequency table reflecting the specific party's usage of words (e.g., a particular band name, such as "U2" being higher in the word frequency table based on a song selected by the user), wherein the adaptation data (e.g., the revised word frequency table) is associated with at least one aspect of the specific party's speech (e.g., the number of times or frequency at which the user speaks one or more words).

Referring again to Figure 7A, operation 504 may include operation 706, which depicts transmitting a phrase completion algorithm to a target device in response to an indication associated with a speech-enabled transaction with a particular party, wherein adaptation data is associated with at least one aspect of the speech of the particular party. For example, Figure 3 (e.g., Figure 3A) illustrates facilitating module 306 transmitting speech adaptation data including a phrase completion algorithm in response to an indication of a speech-enabled transaction with a target device. The facilitating module 306 transmits a phrase completion algorithm to a target device (e.g., a speech-enabled ATM device) in response to an indication associated with a speech-enabled transaction with a particular party (e.g., a user waiting in line to use the speech-enabled ATM device) (e.g., the speech-enabled ATM device detects one or more particular words being spoken by the user), wherein the adaptation data is associated with at least one aspect of the speech of the particular party (e.g., the particular way the user pronounces the word "fifty").

7A , operation 504 may include operation 708, which depicts facilitating transmission of adaptation data to a target device in response to an indication of a particular party's intent to perform a speech-facilitated transaction, wherein the adaptation data is associated with at least one aspect of the particular party's speech. For example, FIG3 (e.g., FIG3A ) illustrates a module 308 for facilitating transmission of speech-adapted data in response to an indication of an intent to perform a speech-facilitated transaction, wherein the module 308 facilitates transmission of adaptation data (e.g., a noise level-dependent filtering algorithm) to a target device (e.g., an auto-pass window) in response to a particular party (e.g., a user in a vehicle) intending to perform a speech-facilitated transaction (e.g., the user drives her vehicle to a particular location that is detected by the system as being close enough to the auto-pass window to place an order), wherein the adaptation data is associated with at least one aspect of the particular party's speech (e.g., associated with the user's previous speech at other auto-pass windows).

Referring again to FIG7A , operation 708 may include operation 710 depicting facilitating transmission of adaptation data to a target device in response to receiving an indication from the target device that a particular party intends to perform a speech-facilitated transaction, wherein the adaptation data is associated with at least one aspect of the speech of the particular party. For example, FIG3 (e.g., FIG3A ) illustrates a module 310 for facilitating transmission of speech-adapted data in response to receiving an indication from a target device that an intent to perform a speech-facilitated transaction, wherein the facilitating module 310 facilitates transmission of adaptation data (e.g., a sentiment-based voice adjustment algorithm) to a target device (e.g., a home security system) in response to receiving an indication from a target device (e.g., a base station of a home security system) that a particular party intends to perform a speech-facilitated transaction (e.g., the particular party begins speaking (e.g., it may be determined later or by another unit whether the user is actually speaking to the target device, but in embodiments such as this one, the target device interprets the speech as an intent by the particular party to initiate a speech-facilitated transaction)), wherein the adaptation data is associated with at least one aspect of the speech of the particular party (e.g., a user's speech patterns detected over a period of time).

7A , operation 710 may include operation 712, which depicts facilitating transmission of adaptation data to a target device in response to receiving an indication from the target device that a particular party pressed a button on the target device. For example, FIG3 (e.g., FIG3A ) illustrates facilitating module 312 for facilitating transmission of speech-adapted data in response to receiving an indication from the target device that a particular party interacted with an input portion of the target device. The facilitating module 312 facilitates transmitting adaptation data (e.g., a syllable pronunciation database) to a target device (e.g., an ATM device) in response to receiving an indication from the target device that a particular party pressed a button on the target device (e.g., a touchscreen button representing “start” on a display of an ATM device).

7A , operation 710 may include operation 714, which depicts facilitating transmission of adaptation data to a target device in response to an indication that a particular party is speaking to the target device. For example, FIG3 (e.g., FIG3A ) illustrates a facilitating module 314 for facilitating transmission of speech-adapted data in response to receiving an indication that a particular party is speaking toward the target device. The facilitating module 314 facilitates transmission of adaptation data (e.g., an accent-based pronunciation modification algorithm) to a target device (e.g., a speech-enabled laptop) in response to an indication that a particular party is speaking to the target device (e.g., in response to receiving a signal indicating that a microphone of the laptop has recorded sounds identified as speech).

Referring now to Figure 7B, operation 710 may include operation 716 depicting facilitating transmission of adaptation data to a target device in response to a request from the target device for adaptation data associated with at least one aspect of speech by a particular party. For example, Figure 3 (e.g., Figure 3A) illustrates a facilitating module 316 for facilitating transmission of speech adaptation data in response to a request for speech adaptation data, facilitating transmission of adaptation data (e.g., a sentence graph path selection algorithm) to a target device (e.g., a speech-enabled television) in response to a request from the target device for adaptation data associated with at least one aspect of speech by a particular party (e.g., adaptation data derived from a previous speech command given to a television owned by a user).

7B , operation 708 may include operation 718, which depicts facilitating transmission of adaptation data to a target device in response to receiving an indication from a specific device associated with the specific party that the specific party intends to perform a speech-enabled transaction, wherein the adaptation data is associated with at least one aspect of the speech of the specific party. For example, FIG3 (e.g., FIG3B ) illustrates facilitating transmission of speech-adapted data 318 in response to receiving an indication from a specific device that the specific party intends to perform a speech-enabled transaction, wherein the facilitating module 318 facilitates transmission of adaptation data (e.g., an uncommon word pronunciation guide) to a target device (e.g., a speech-enabled microwave oven) in response to receiving an indication from a specific device (e.g., a key fob having a chip and memory configured to send, receive, and store adaptation data) associated with the specific party (e.g., carried by the specific party) that the specific party intends to perform a speech-enabled transaction (e.g., commanding a microwave oven to defrost for five minutes), wherein the adaptation data is associated with at least one aspect of the speech of the specific party (e.g., a previous speech interaction of the specific party).

7C , operation 504 may include operation 720, which depicts sending first adaptation data associated with a first aspect of the speech of the particular party to a target device. For example, FIG3 (e.g., FIG3C ) illustrates module 320 for sending first speech adaptation data associated with a first aspect of the speech of the particular party to a target device, which module 320 sends first adaptation data (e.g., an accent-based pronunciation modification algorithm) associated with a first aspect of the speech of the particular party (e.g., an accent based on where the particular party is from) to a target device (e.g., a speech-enabled audio/video receiver).

Referring again to FIG7C , operation 504 may include operation 722, which depicts sending second adaptation data associated with a second aspect of the speech of the particular party to the target device before completing the speech-facilitated transaction for the particular party. For example, FIG3 (e.g., FIG3C ) shows module 322 sending second speech adaptation data associated with a second aspect of the speech of the particular party to the target device, which module 322 sends second adaptation data (e.g., a different accent-based pronunciation correction algorithm) associated with the second aspect of the speech of the particular party (e.g., based on the user's pronunciation of a set of words, such as "volume," "source," "play," and "fast forward") before the speech-facilitated transaction for the particular party is completed (e.g., before the speech-facilitated transaction ends). In one example, if an audio/video receiver encounters difficulty interpreting speech based on first adaptation data (which may be accent-based), the receiver may request additional adaptation data, which may be based on a previous pronunciation.

7C , operation 720 may include operation 724, which depicts sending first adaptation data associated with the particular party's accent to a target device. For example, FIG. 3 (e.g., FIG. 3C ) illustrates module 324 for sending first speech adaptation data associated with the particular party's speaking style to a target device, which sends first adaptation data associated with the particular party's accent to a target device (e.g., a motor vehicle assistance/dialing system, such as OnStar).

7C , operation 720 may include operation 726, which depicts sending first adaptation data associated with the expected vocabulary of the particular party to the target device. For example, FIG3 (e.g., FIG3C ) illustrates module 326 sending first speech adaptation data associated with the expected vocabulary to the target device. Module 326 sends first adaptation data associated with the expected vocabulary of the particular party (e.g., pronunciation guides for words that may be used in transactions, such as “money,” “checkout,” and “save”) to the target device (e.g., an automated teller machine device).

7C , operation 726 may include operation 728, which depicts sending first adaptation data including a party-specific vocabulary expected to be used during a speech-facilitated transaction to a target device. For example, FIG3 (e.g., FIG3C ) illustrates module 328 sending first speech adaptation data associated with vocabulary estimated to be used during a speech-facilitated transaction to a target device. Module 328 sends first adaptation data including a party-specific vocabulary (e.g., pronunciation of street names, city names, and proper names) expected to be used during a speech-facilitated transaction (e.g., navigation to a place) to a target device (e.g., a personal navigation system mounted on a car windshield).

7C , operation 728 may include operation 730, which depicts sending first adaptation data for a pronunciation dictionary including one or more words associated with food items expected to be used during a speech-facilitated transaction to a target device, the target device being an automated pass-through order taking device. For example, FIG3 (e.g., FIG3C ) illustrates module 330 sending first speech adaptation data associated with one or more words associated with food items expected to be used during a speech-facilitated transaction to a target device. Module 330 sends first adaptation data for a pronunciation dictionary including one or more words associated with food items expected to be used during a speech-facilitated transaction (e.g., “hamburger,” “bacon,” “beef burger”) to a target device, the target device being an automated pass-through order taking device.

7 , operation 728 may include operation 732, which depicts sending first adaptation data for a pronunciation lexicon including one or more electronics and media words expected to be used during a speech-facilitated transaction to a target device, the target device being a speech-enabled media player. For example, FIG3 (e.g., FIG3C ) illustrates module 332 sending first speech adaptation data associated with one or more words associated with one or more electronics expected to be used during a speech-facilitated transaction to a target device, the module 332 sending first adaptation data for a pronunciation lexicon including one or more electronics and media words expected to be used during a speech-facilitated transaction (e.g., interacting with a media player) to a target device, the target device being a speech-enabled media player.

7D , operation 720 may include operation 734, which depicts sending first adaptation data associated with the language spoken by the particular party. For example, FIG3 (e.g., FIG3D ) illustrates module 334 sending first speech adaptation data associated with the spoken language to the target device. Module 334 sends first adaptation data associated with the language spoken by the particular party (e.g., the user is a French speaker) (e.g., the first adaptation data takes the French spoken by the user and converts it into an English equivalent that the device understands).

7D , operation 720 may include operation 736, which depicts sending first adaptation data based on a previous speech-facilitated transaction by a group member having at least one common property with the particular party. For example, FIG3 (e.g., FIG3D ) illustrates module 336 sending first speech adaptation data associated with a previous speech-facilitated transaction to a target device by a group member having a particular property, wherein module 336 sends first adaptation data (e.g., a phoneme pronunciation database) based on a previous speech-facilitated transaction by a group member having at least one common property (e.g., common ancestry) with the particular party.

7D , operation 736 may include operation 738, which depicts sending, by members of a group originating from the same geographic region as the particular party, first adaptation data based on previous speech-facilitating transactions. For example, FIG3 (e.g., FIG3D ) illustrates module 338 sending, by members of a group from a particular community, first speech adaptation data associated with previous speech-facilitating transactions to a target device, which module 338 sends, by members of a group originating from the same geographic region as the particular party (e.g., “Southern United States”), first adaptation data (e.g., a basic pronunciation adjustment algorithm) based on previous speech-facilitating transactions.

Referring back to FIG7C , operation 722 may include operation 740, which depicts sending second adaptation data associated with a second aspect of the speech of the particular party to the target device in response to a request from the target device before completing the speech-facilitated transaction for the particular party. For example, FIG3 (e.g., FIG3C ) illustrates module 340 for sending second speech adaptation data associated with a second aspect of the speech of the particular party in response to a request from the target device, which module 340 sends second adaptation data (e.g., a regional dialect application algorithm) associated with a second aspect of the speech of the particular party (e.g., a user-specific accent based on the user's previous speech interactions) to a target device (e.g., a ticket vending machine) in response to a request from the target device (e.g., the target device may not be able to quickly interpret the speech using only the first adaptation data, so the target device requests the second adaptation data) before completing the speech-facilitated transaction for the particular party.

7D , operation 722 may include operation 742, which depicts sending second adaptation data associated with a second aspect of speech that is different from the first aspect of speech of the particular party to a target device before the transaction facilitated by the particular party is completed. For example, FIG3 (e.g., FIG3C ) illustrates module 342 sending second speech adaptation data associated with a second aspect that is different from the first aspect to a target device, which module 342 sends second adaptation data (e.g., a speech part labeling algorithm) associated with a second aspect of speech that is different from the first aspect of speech of the particular party (e.g., an accent of a group of people of which the particular party is a part) to a target device (e.g., a motor vehicle control system) before the transaction facilitated by the particular party is completed.

7D , operation 742 may include operation 744, which depicts sending second adaptation data prior to completion of the speech-facilitated transaction, wherein the second adaptation data is based on prior speech interactions of a second group of people, and the first adaptation data is based on prior speech interactions of a first group of people. For example, FIG3 ( FIG3C ) illustrates sending to a target device second speech adaptation data associated with a first, different set of prior speech interactions associated with the first speech adaptation data, the module 344 sending the second adaptation data (e.g., a second pronunciation adjustment algorithm, wherein the first adaptation data is a first, different pronunciation adjustment algorithm) prior to completion of the speech-facilitated transaction, wherein the second adaptation data is based on prior speech interactions of a second group of people (e.g., people of a particular ethnic background), and the first adaptation data is based on prior speech interactions of a first group of people (e.g., a group of people who grew up in a particular city).

7D , operation 744 may include operation 746 of sending second adaptation data prior to completion of the speech-facilitated transaction, wherein the second adaptation data is based on prior speech interactions of a second group of people that is smaller than the first group of people. For example, FIG3 (e.g., FIG3C ) shows second speech adaptation data associated with prior speech interactions of a second group that is smaller than the first group associated with the first speech adaptation data being sent to a module 346 of a target device, the module 346 sending second adaptation data (e.g., a second pronunciation adjustment algorithm designed to modify a first pronunciation adjustment algorithm) prior to completion of the speech-facilitated transaction, wherein the second adaptation data is based on prior speech interactions of a second group of people (e.g., a group of people directly associated with a particular party for whom the prior speech interactions were detected and analyzed) that is smaller than the first group of people (e.g., a group of people who grew up in a particular city).

Figures 8A-8G depict various implementations of operation 506 according to embodiments. Referring now to Figure 8A , operation 506 includes operation 802, which depicts updating adaptation data, the updating being based at least in part on the results of at least a portion of the speech-favored transaction. For example, Figure 4 (e.g., Figure 4A ) illustrates module 402 modifying speech adaptation data based in part on the results of a portion of the speech-favored transaction, which updates (e.g., modifies at least a portion thereof, even if it is as minor as changing a "last used date" stored in the adaptation data) adaptation data (e.g., a sentence graph routing algorithm), the updating being based at least in part on the results of at least a portion of the speech-favored transaction (e.g., administering a speech command to an automated teller machine device) (e.g., how quickly the target device was able to process speech using the sentence graph routing algorithm).

8A , operation 506 may include operation 804, which depicts determining not to update adaptation data, the determination being based at least in part on the results of at least a portion of the speech-facilitated transaction. For example, FIG4 (e.g., FIG4A ) illustrates module 404 for determining not to modify speech adaptation data based in part on the results of at least a portion of the speech-facilitated transaction, the module 404 determining not to update adaptation data (e.g., uncommon word pronunciation guides), the determination being based at least in part on the results of at least a portion of the speech-facilitated transaction (e.g., user feedback indicating that the user was “very happy” with the transaction).

Referring again to Figure 8A, operation 506 may include operation 806, which depicts determining whether to update the adaptation data, the determination being based at least in part on the results of the completed speech-facilitating transaction. For example, Figure 4 (e.g., Figure 4A) illustrates module 406 for determining possible revisions to speech adaptation data based at least in part on the results of the completed speech-facilitating transaction, the module 406 determining whether to update the adaptation data (e.g., a non-dictionary word removal algorithm), the determination being based at least in part on the results of the completed speech-facilitating transaction (e.g., the results of the completed transaction interacting with the motor vehicle control system are sent to a remote server, and at a later date, the transaction is analyzed to determine how successful the transaction was in removing non-dictionary words).

8A , operation 506 may include operation 808, which depicts determining whether to update adaptation data, the determination being based at least in part on the results of the initial portion of the speech-facilitated transaction. For example, FIG4 (e.g., FIG4A ) illustrates module 408 for determining possible revisions to speech adaptation data based in part on the results of the initial portion of the speech-facilitated transaction. The module 408 determines whether to update adaptation data (e.g., a speech disfluency detection algorithm) based at least in part on the results of the initial portion (e.g., the first two sentences of the transaction) of a speech-facilitated transaction (e.g., withdrawing money from a speech-enabled automated teller machine).

8A , operation 506 may include operation 810, which depicts determining whether to update adaptation data, wherein a speech-facilitating transaction includes a first sentence and a second sentence, and the determining occurs after the first sentence and before the second sentence. For example, FIG4 (e.g., FIG4A ) illustrates a determination module 410 for determining whether to update adaptation data (e.g., a context-based repaired speech processing matrix) based in part on a possible revision of speech adaptation data for a first sentence of a speech-facilitating transaction that occurs before a second sentence of the speech-facilitating transaction, wherein the speech-facilitating transaction (e.g., issuing a command to a motor vehicle control system) includes a first sentence (e.g., “Play Norah Jones”) and a second sentence (e.g., “Turn the volume up to 25”), and the determining occurs after the first sentence and before the second sentence.

8A , operation 506 may include operation 812, which depicts determining how to update adaptation data, said determination being made before the speech-facilitated transaction is completed. For example, FIG4 (e.g., FIG4A ) illustrates module 412 for determining whether to update adaptation data (e.g., discussant detection module) based in part on the results of a portion of the speech-facilitated transaction and made before the speech-facilitated transaction is concluded, said module 412 determining whether to update adaptation data (e.g., discussant detection module), said determination being made before the speech-facilitated transaction is completed (e.g., after the user completes his order at the auto-pass window).

Referring again to Figure 8A, operation 506 may include operation 814, which depicts determining whether to update adaptation data after at least one word is spoken in a speech-facilitated transaction. For example, Figure 4 (e.g., Figure 4A) illustrates module 414 for determining possible revisions to speech adaptation data based in part on the results of a portion of a speech-facilitated transaction after at least one word is spoken by a particular party, the module 414 determining whether to update adaptation data (e.g., a speech portion tagging algorithm), the determination made after at least one word is spoken in a speech-facilitated transaction (e.g., dictating a transcript to a computer configured to receive speech as input).

Referring again to Figure 8A, operation 814 may include operation 816, which depicts determining whether to update adaptation data, the determination occurring before a particular word is spoken in a speech-facilitated transaction. For example, Figure 4 (e.g., Figure 4A) illustrates module 416 for determining a possible revision of speech adaptation data based in part on the results of a portion of a speech-facilitated transaction and made before a particular word. The module 416 determines whether to update adaptation data (e.g., a portion of a pattern tree model) the determination occurring before a particular word is spoken in a speech-facilitated transaction (e.g., before the word "bye" is spoken in a transaction that may end with the word "bye").

8B , operation 506 may include operation 818, which depicts receiving a result of at least a portion of the speech-enabled transaction. For example, FIG4 (e.g., FIG4B ) illustrates a portion of a speech-enabled transaction result acquisition module 418, which receives a result (e.g., an indication of whether or how successful the interpretation of the portion of the transaction was successful, or an estimate of how likely the device was to determine that the transaction was successful) of at least a portion (e.g., a first sentence spoken by a user and interpreted by the speech-enabled ticketing device) of a speech-enabled transaction (e.g., printing a ticket at an airport using a speech-enabled ticketing device).

Referring again to FIG8B , operation 506 may include operation 820 , which depicts determining whether to update the adaptation data, the determination being based at least in part on the received results. For example, FIG4 (e.g., FIG4B ) illustrates module 420 for determining possible revisions to speech adaptation data based in part on the obtained results. The module 420 determines whether to update the adaptation data (e.g., a potential conversation interaction matrix), the determination being based at least in part on the received results (e.g., the amount by which the potential conversation interaction matrix is to be revised is based on the received indication of how successful the transaction portion was).

8B , operation 818 may include operation 822, which depicts receiving a result of at least a portion of the speech-facilitated transaction from the target device. For example, FIG4 (e.g., FIG4B ) illustrates module 422 for obtaining a portion of the speech-facilitated transaction result from the target device, which module 422 receives a result of at least a portion of the speech-facilitated transaction (e.g., a command given to the portable navigation system) from the target device (e.g., the portable navigation system sending an estimate) (e.g., an estimate that speech completion takes 72% longer than the average portion of the speech-facilitated transaction).

8B , operation 818 may include operation 824, which depicts receiving a result of at least a portion of the speech-favored transaction from a particular party. For example, FIG4 (e.g., FIG4B ) illustrates module 424 for obtaining a portion of the speech-favored transaction from a particular party, which module 424 receives a result (e.g., the transaction interpretation being rated as "poor") of at least a portion of the speech-favored transaction (e.g., ordering spring soda from an automated beverage preparation machine device) from a particular party (e.g., a user indicating that the transaction interpretation is "poor").

Referring again to Figure 8B, operation 824 may include operation 826, which depicts receiving a result of at least a portion of a speech-facilitated transaction from a specific party interacting with a specific device configured to manage adaptation data. For example, Figure 4 (e.g., Figure 4B) illustrates module 426 for obtaining a portion of a speech-facilitated transaction result from a specific device operated by a specific party, the module 426 receiving a result of at least a portion of a speech-facilitated transaction (e.g., commanding a motor vehicle control system to lower a rear window and open a sunshade) from a specific party interacting with a specific device configured to manage adaptation data (e.g., a word and/or syllable dependency analyzer) (e.g., a key fob inserted into a vehicle and configured to store, send, and receive adaptation data and associated with a specific driver).

Referring again to Figure 8B, operation 826 may include operation 828, which depicts receiving a result of at least a portion of the speech-facilitated transaction from a particular party pressing a button on a particular device configured to manage adaptation data. For example, Figure 4 (e.g., Figure 4B) illustrates module 428 for obtaining a portion of the speech-facilitated transaction result at least in part as a result of pressing a button on a particular device, which module 428 receives a result of at least a portion of the speech-facilitated transaction (e.g., an indication that the speech-facilitated transaction failed) from a particular party (e.g., a user) pressing a button on a particular device (e.g., a user's smartphone) (e.g., a button that reads "Press here if the device you wish to communicate with is having trouble processing your speech") that is configured to manage adaptation data (e.g., a smartphone manages the user's adaptation data, such as an ungrammatical utterance removal algorithm).

8B , operation 826 may include operation 830, which depicts receiving, after the speech-facilitated transaction is concluded, a result of at least a portion of the speech-facilitated transaction from a particular party that provided feedback to a particular device. For example, FIG4 (e.g., FIG4B ) illustrates module 430 for obtaining a portion of speech-facilitated transaction feedback from a particular device operated by the particular party, wherein module 430 receives, after the speech-facilitated transaction is concluded (e.g., after the speech-facilitated transaction is concluded and the summary is sent to the cell phone and adopted by the user), a result of at least a portion of the speech-facilitated transaction (e.g., purchasing a train ticket at a train station) (e.g., a summary result in which the speech-facilitated transaction was rated 1 out of 5) from a particular party (e.g., a user purchasing a ticket) that provided feedback to the particular device (e.g., filling out a summary displayed on a screen of the cell phone).

8B , operation 818 may include operation 832, which depicts receiving an indication that at least a portion of the speech-enabled transaction was unsuccessful. For example, FIG. 4 (e.g., FIG. 4B ) illustrates acquisition module 432 indicating a portion of a speech-enabled transaction outcome that was less than a complete success, where acquisition module 432 receives an indication that at least a portion of the speech-enabled transaction was unsuccessful (e.g., receives an indication that the first three sentences spoken by the user in the transaction could not be parsed into commands understood by the device).

8B , operation 832 may include operation 834, which depicts receiving an indication that at least a portion of the speech-facilitated transaction was not successfully interpreted by the target device. For example, FIG4 (e.g., FIG4B ) illustrates capture module 434 of a portion of a speech-facilitated transaction result indicating an incomplete or low-confidence interpretation of a portion of the transaction, where capture module 434 receives an indication that at least a portion of the speech-facilitated transaction (e.g., a command to lower the ambient temperature in a room control system) was not successfully interpreted (e.g., the command failed) by a target device (e.g., an automated teller machine device).

8C , operation 818 may include operation 836, which depicts receiving an indication that the device has determined that at least a portion of the speech-enabled transaction was unsuccessful. For example, FIG4 (e.g., FIG4C ) illustrates an acquisition module 436 of a portion of a speech-enabled transaction result indicating that at least a portion of the speech-enabled transaction failed to be performed by a target device, where the acquisition module 436 receives an indication that a target device (e.g., an automated ticketing device) has determined that at least a portion of the speech-enabled transaction (e.g., a first portion of the transaction in which a user attempted to identify a city to which they wish to travel) was unsuccessful (e.g., the device was unable to locate a city spoken by the user).

8C , operation 836 may include operation 838, which depicts receiving an indication that the target device interpreted at least a portion of the speech-enabled transaction with an error rate above a particular threshold. For example, FIG4 (e.g., FIG4C ) illustrates acquisition module 436 indicating that the target device determined a portion of the speech-enabled transaction result with an error rate above a threshold. Acquisition module 436 receives an indication that the target device (e.g., a speech-enabled copier device operating on an office enterprise network) interpreted at least a portion of the speech-enabled transaction (e.g., a command to change from "black and white" to "color") with an error rate above a particular threshold (e.g., it took four attempts for the user's command to be understood).

8C , operation 836 may include operation 840, which depicts receiving an indication that the target device interpreted at least a portion of the speech-enabled transaction with a confidence rate below a particular threshold. For example, FIG. 4 (e.g., FIG. 4C ) illustrates an acquisition module 440 instructing the target device to determine a portion of the speech-enabled transaction result with a confidence rate below a threshold. The acquisition module 440 receives an indication that the target device (e.g., a personal navigation system) interpreted at least a portion of the speech-enabled transaction (e.g., the name of a restaurant that a user was trying to find) with a confidence rate below a particular threshold (e.g., the device has a confidence rate of less than 25% that it identified the correct location).

8C , operation 818 may include operation 842, which depicts receiving an indication from a particular party that notifies a target device that at least a portion of the speech-enabled transaction was unsuccessful. For example, FIG4 (e.g., FIG4C ) illustrates module 442 for obtaining a portion of the speech-enabled transaction result from a particular party via a target device, wherein module 442 receives an indication from a particular party that notifies a target device (e.g., a speech-enabled automated teller machine device) that at least a portion of the speech-enabled transaction (e.g., a portion selecting an amount of money to be withdrawn) was unsuccessful (e.g., a user pressing a button indicating that none of the amounts displayed on the screen are the amounts claimed by the user).

8C , operation 818 may include operation 844, which depicts receiving a result of at least a portion of a speech-facilitated transaction, the result including a list of one or more words that were successfully interpreted. For example, FIG. 4 (e.g., FIG. 4C ) illustrates a portion of a speech-facilitated transaction including one or more interpreted words, where the capture module 444 receives a result (e.g., a list of one or more words that were part of the transaction and were successfully interpreted) of at least a portion of a speech-facilitated transaction (e.g., a portion of an auto-pass window order).

8C , operation 818 may include operation 846, which depicts receiving a result of at least a portion of a speech-facilitated transaction, the result including a list of one or more words that were not successfully interpreted. For example, FIG4 (e.g., FIG4C ) illustrates an acquisition module 446 of a portion of a speech-facilitated transaction result including one or more words that were not fully interpreted, the acquisition module 446 receiving a result (e.g., a data structure containing one or more unsuccessfully interpreted words (e.g., based on a preliminary impression)) of at least a portion (e.g., a paragraph thereof) of a speech-facilitated transaction (e.g., a legal transcript of a user's use of speech to a speech-enabled computer operating on a home network).

8C , operation 818 includes operation 848, which depicts receiving a result of at least a portion of a speech-facilitated transaction, the result including a pronunciation of one or more words spoken by a particular party during the speech-facilitated transaction. For example, FIG4 (e.g., FIG4C ) illustrates a capture module 448 of a portion of a speech-facilitated transaction result including a representation of one or more words spoken by a particular party during the speech-facilitated transaction. The capture module 448 receives a result (e.g., a device obtains a waveform audio file (WAV file) of a user's pronunciation of one or more words that the device cannot interpret or takes more than one attempt to interpret) of at least a portion of a speech-facilitated transaction (e.g., a transaction including several steps to set up a home theater setup, such as adjusting the sound to surround sound, reducing brightness and contrast, and tuning the video input to a Blu-ray player) including a pronunciation of one or more words spoken by the particular party (e.g., the words "play the movie 'Inception'").

8D , operation 818 may include operation 850, which depicts receiving a result of at least a portion of the speech-enabled transaction, the result including a pronunciation of one or more words interpreted by the target device during the speech-enabled transaction. For example, FIG. 4 ( FIG. 4D ) illustrates an acquisition module 450 of a portion of a speech-enabled transaction result including a representation of one or more words interpreted by the target device for the speech-enabled transaction, the acquisition module 450 receiving a result of at least a portion of the speech-enabled transaction (e.g., a voice command given to a speech-enabled television), the result including a pronunciation of one or more words interpreted by the target device during the speech-enabled transaction (e.g., “power off”).

8D , operation 818 may include operation 852, which depicts receiving results of at least a portion of a speech-facilitated transaction, the results comprising a table of one or more words interpreted during the speech-facilitated transaction and pronunciations of the one or more interpreted words by a particular party. For example, FIG4 (e.g., FIG4D ) illustrates a portion of a speech-facilitated transaction results acquisition module 452 comprising a data structure configured to store one or more interpreted words of the speech-facilitated transaction and one or more corresponding representations of the pronunciations of the one or more interpreted words, the acquisition module 452 receiving results of at least a portion of a speech-facilitated transaction, the results comprising a table of one or more words interpreted during the speech-facilitated transaction and pronunciations of the one or more interpreted words by a particular party (e.g., a user).

8D , operation 506 may include operation 854, which depicts receiving a result of at least a portion of the speech-facilitated transaction. For example, FIG4 (e.g., FIG4D ) illustrates module 454 receiving a result of at least a portion of the speech-facilitated transaction (e.g., an indication that interpretation of speech was successful) for at least a portion of the speech-facilitated transaction (e.g., commands given to a video game played on a speech-enabled video game system through a microphone (e.g., a headset)).

8D , operation 506 may include operation 856, which depicts updating the adaptation data based on the results of at least a portion of the speech-facilitated transaction. For example, FIG4 (e.g., FIG4D ) illustrates module 456 for modifying speech adaptation data based at least in part on at least a portion of the received results, where module 456 updates adaptation data (e.g., a random state transition network) based on the results of at least a portion of the speech-facilitated transaction (e.g., giving commands to a video game played on a speech-enabled video game system through a microphone (e.g., a headset).

8D , operation 506 may include operation 858, which depicts sending updated adaptation data to the target device before the speech-facilitated transaction is completed. For example, FIG4 (e.g., FIG4D ) illustrates module 458 for sending updated speech adaptation data before the speech-facilitated transaction is completed, which sends updated adaptation data (e.g., a random state transition network having at least one updated or changed state transition path) to the target device before the speech-facilitated transaction ends (e.g., before the user issues the last command in a series of commands to the game).

8D , operation 506 may include operation 860, which depicts receiving a result of at least a portion of the speech-facilitated transaction. For example, FIG4 (e.g., FIG4D ) illustrates module 456 receiving a result of at least a portion of the speech-facilitated transaction (e.g., an indication of whether the interpretation of the speech was successful) of at least a portion of the speech-facilitated transaction (e.g., a portion of a user ordering a double cheeseburger, fries, and iced tea through a drive-through window).

8D , operation 506 may include operation 862, which depicts updating the adaptation data based on the results of at least a portion of the speech-facilitated transaction. For example, FIG4 (e.g., FIG4D ) illustrates module 458 for modifying speech adaptation data based in part on the results of updating the adaptation data (e.g., changing the pronunciation of one or more words in the pronunciation dictionary, such as the word "double") based on the results of at least a portion of the speech-facilitated transaction (e.g., placing the first portion of an order in which the user ordered a "double cheeseburger").

8D , operation 506 may include operation 864, which depicts receiving a result of at least a portion of the speech-enabled transaction. For example, FIG4 (e.g., FIG4D ) illustrates an obtaining module 464 for obtaining at least a portion of the result of a portion of the speech-enabled transaction, which receives a result (e.g., an indication of a target device inference regarding whether the interpretation was successful) of at least a portion of the speech-enabled transaction (e.g., a user giving a command to an ATM device).

8D , operation 506 may include operation 866, which depicts updating the adaptation data based on the outcome of at least a portion of the speech-facilitated transaction. For example, FIG4 (e.g., FIG4D ) illustrates module 466 for updating speech adaptation data based at least in part on at least a portion of the received outcome, which updates adaptation data (e.g., a phoneme pronunciation database) based on the outcome (e.g., an inference made by the ATM device as to whether the interpretation was successful) of at least a portion of the speech-facilitated transaction (e.g., a user providing a personal identification number (PIN) to the ATM device).

8D , operation 506 may include operation 868, which depicts sending a signal indicating that the adaptation data has been updated. For example, FIG4 (e.g., FIG4E ) illustrates the sending module 468 of a signal indicating adaptation of speech adaptation data, which sends a signal indicating that the adaptation data (e.g., an utterance ignoring algorithm) has been updated (e.g., additional utterances to be ignored have been added to the algorithm).

8E , operation 506 may include operation 870, which depicts receiving update data regarding updated adaptation data from another device. For example, FIG. 4 (e.g., FIG. 4E ) illustrates module 470 for receiving possible correction data from another device, which receives update data (e.g., data indicating how to correct the pronunciation dictionary) regarding updated adaptation data (e.g., regarding correcting the pronunciation of a word in the pronunciation dictionary) from another device (e.g., a remote server).

8E , operation 506 may include operation 872, which depicts updating the adaptation data based on the received update data. For example, FIG. 4 (e.g., FIG. 4D ) illustrates module 472 for applying possible correction data received from another device to speech adaptation data, and module 472 updates the adaptation data (e.g., a modified pronunciation dictionary) based on the received update data (e.g., data indicating how to modify the pronunciation dictionary).

8E , operation 506 may include operation 874, which depicts receiving a result of at least a portion of the speech-facilitated transaction. For example, FIG4 (e.g., FIG4E ) illustrates speech-facilitated transaction result portion receiving module 474, which receives a result of at least a portion of the speech-facilitated transaction (e.g., a command to the home theater system) (e.g., a series of commands to the home theater system).

8E , operation 506 may include operation 876, which depicts sending the result of at least a portion of the speech-facilitated transaction to another location. For example, FIG4 (e.g., FIG4E ) illustrates module 476 for sending a portion of the speech-facilitated transaction result to a device, which sends the result of at least a portion of the speech-facilitated transaction (e.g., a command given to the home theater system) (e.g., an indication of whether the interpretation of the speech-facilitated transaction was successful) to another location (e.g., to a computer at home that is networked to one or more devices of the home theater system).

Referring again to Figure 8E, operation 506 may include operation 878, which depicts receiving update data from another location, the update data including an indication of whether to update the adaptation data. For example, Figure 4 (e.g., Figure 4E) illustrates module 478 for indicating whether to modify the determination data of speech adaptation data received from the device, the module 478 receiving update data from another location (e.g., a home computer networked with one or more devices), the update data including an indication of whether to update (e.g., whether to modify) the adaptation data (e.g., a phrase completion algorithm).

Referring again to Figure 8E, operation 876 may include operation 880, which depicts sending the results of at least a portion of the speech-facilitated transaction to another location that also stores adaptation data. For example, Figure 4 (e.g., Figure 4E) shows module 480 sending a portion of the speech-facilitated transaction results to a device that stores speech adaptation data. Module 480 sends the results of at least a portion of the speech-facilitated transaction (e.g., a command given to a home theater system) (e.g., a score indicating how efficiently speech given to a command given to the home theater system was processed) to another location that also stores adaptation data (e.g., a remote cloud server).

Referring again to Figure 8E, operation 878 may include operation 882, which depicts receiving update data from another location, the update data further including instructions for updating the adaptation data. For example, Figure 4 (e.g., Figure 4E) shows module 482 that instructs how to modify the determination data of speech adaptation data received from the device, the module 482 receiving update data (e.g., instructions for modifying a phoneme database) from another location (e.g., a dedicated computer for processing potential changes to adaptation data in an enterprise network setting), the update data including instructions for updating the adaptation data (e.g., phoneme database).

Referring again to Figure 8E, operation 506 may include an operation depicting receiving a result of at least a portion of the speech-enabled transaction, operation 884. For example, Figure 4 (e.g., Figure 4E) illustrates a speech-enabled transaction result portion receiving module 848 that receives a result (e.g., a separate program running on a computer and determining the efficiency of speech processing performed by the computer) of at least a portion of the speech-enabled transaction (e.g., executing a set of commands to customize an Internet browser on a speech-enabled computer).

Referring again to Figure 8E, operation 506 may include operation 886, which depicts determining to update adaptation data based at least in part on the results of at least a portion of the speech-facilitated transaction. For example, Figure 4 (e.g., Figure 4E) illustrates module 486 for making speech adaptation data modification decisions based in part on the results of the speech-facilitated transaction, which module 486 determines to update adaptation data (e.g., a sentence graph path selection algorithm) based at least in part on the results of at least a portion of the speech-facilitated transaction (e.g., the first command in the transaction to customize the browser, e.g., to load a customized homepage or front page).

8E , operation 506 may include operation 888, which depicts sending a request to update the adaptation data to another location. For example, FIG4 (e.g., FIG4E ) illustrates module 488 requesting that the modified speech adaptation data be sent to the device, which module 488 sends a request to update the adaptation data (e.g., the sentence graph path selection algorithm) to another location (e.g., to a remote server operated by the developer of the operating system on which the browser is running).

Referring again to Figure 8E, operation 506 may include operation 890, which depicts receiving updated adaptation data from another location. For example, Figure 4 (e.g., Figure 4E) shows module 490 for obtaining revised adaptation data from a device, which receives updated adaptation data (e.g., a revised or changed sentence graph path selection algorithm) from another location (e.g., from a remote server that revised the adaptation data based on a number of speech interactions of the user).

8E , operation 506 may include operation 891 depicting receiving a result of at least a portion of a speech-facilitating transaction, wherein the result indicates that the speech-facilitating transaction is moving too fast for the speech to be fully processed. For example, FIG4 (e.g., FIG4E ) illustrates module 491 of possible correction data for a slowdown request from a device, which receives a result of at least a portion of a speech-facilitating transaction, wherein the result indicates that the speech-facilitating transaction is moving too fast for the speech to be fully processed (e.g., the speaker is speaking too fast and the target device is unable to keep up with the processing).

8E , operation 506 may include operation 893, which depicts facilitating presentation of a video or audio indication to the particular party instructing the particular party to slow down to facilitate the transaction. For example, FIG4 (e.g., FIG4E ) illustrates facilitating presentation of a slow down indication module 493, which facilitates presenting (e.g., either on a particular device associated with the user (e.g., a smartphone) or through a device through which the user facilitates the transaction (e.g., an auto-pass window)) a video or audio indication (e.g., a beep or a yellow or red light) to the particular party instructing the particular party to slow down (e.g., either stop speaking for a certain amount of time or slow down the tone of the user's voice) to facilitate the transaction.

Referring now to Figure 8F, operation 506 may include operation 892, which depicts receiving the results of the first portion of the speech-enabled transaction. For example, Figure 4 (e.g., Figure 4F) illustrates the acquisition module 492 of the results of a particular portion of the speech-enabled transaction, which receives the results of the first portion of the speech-enabled transaction (e.g., the first sentence of interacting with the ticket vending machine (e.g., authenticating yourself for security purposes)).

Referring again to Figure 8F, operation 506 may include operation 894, which depicts updating the adaptation data based at least in part on the results of the first portion of the speech-facilitating transaction. For example, Figure 4 (Figure 4F) illustrates applying a possible modification 494 of speech adaptation data based at least in part on the results of obtaining a particular portion of the speech-facilitating transaction, which updates (e.g., changes a parameter of) adaptation data (e.g., a regional dialect application algorithm) based at least in part on the results of the first portion of the speech-facilitating transaction (e.g., whether the device was able to effectively identify the user and detect speech presented to the device).

8F , operation 506 may include operation 896, which depicts sending updated adaptation data to the target device, the updated adaptation data being configured to be applied by the target device before the second portion of the speech-facilitated transaction concludes. For example, FIG4 (e.g., FIG4F ) illustrates a sending module 496 configured to apply revised speech adaptation data to another portion of the speech-facilitated transaction by the target device, the sending module 496 sending updated adaptation data (e.g., a regional dialect application algorithm with revised parameters) to the target device (e.g., a ticket vending machine), the updated adaptation data being configured to be applied by the target device (e.g., a ticket vending machine) before the second portion of the speech-facilitated transaction (e.g., the user giving her destination city information) concludes.

Referring again to Figure 8F, operation 894 may include operation 898, which depicts changing the algorithm for adapting the data based at least in part on the results of the first portion of the speech-facilitated transaction. For example, Figure 4 (e.g., Figure 4F) illustrates module 496 for applying an algorithm for potentially modifying speech adaptation data based at least in part on the results of obtaining a particular portion of the speech-facilitated transaction, wherein module 496 at least in part modifies the algorithm for adapting the data (e.g., switching from a regional dialect application algorithm to an accent-based pronunciation modification algorithm) based at least in part on the results of the first portion of the speech-facilitated transaction (e.g., an error rate greater than 25% for the first portion of the transaction, which triggers the algorithm to switch).

Referring again to Figure 8F, operation 898 may include operation 801, which depicts modifying at least one parameter of at least one algorithm for adapting the data based at least in part on the results of the first portion of the speech-facilitating transaction. For example, Figure 4 (e.g., Figure 4F) illustrates module 401 for applying a parameter of an algorithm for potentially modifying speech adaptation data based at least in part on the results of acquiring a particular portion of the speech-facilitating transaction. Module 401 modifies at least one parameter of at least one algorithm for adapting the data (e.g., changing the amount of an attenuation parameter of a noise-level-dependent filtering algorithm) based at least in part on the results of the first portion of the speech-facilitating transaction (e.g., indicating that there were too many false positives for a word segment, and therefore the parameter should be adjusted).

8F , operation 896 may include operation 803, which depicts using a different algorithm for adapting the data based at least in part on the results of the first portion of the speech-facilitated transaction. For example, FIG4 (e.g., FIG4F ) illustrates module 403 for selecting a different algorithm for speech adaptation data based at least in part on the results of acquiring a particular portion of the speech-facilitated transaction, the module 403 using a different algorithm for adapting the data (e.g., switching from a non-lexicon word removal algorithm to a speech disfluency detection algorithm) based at least in part on the results of the first portion of the speech-facilitated transaction (e.g., a result indicating that the algorithm did not do anything useful because no non-lexicon words were detected).

Referring now to Figure 8G , operation 894 may include operation 805, which depicts modifying the pronunciation dictionary as part of the adaptation data, the modification being based at least in part on the results of the first portion of the transaction facilitating speech. For example, Figure 4 (e.g., Figure 4G ) illustrates module 405 for applying possible modifications to the pronunciation dictionary based at least in part on the results of obtaining a particular portion of the transaction facilitating speech, the module 405 modifying the pronunciation dictionary as part of the adaptation data, the modification being based at least in part on the results of the first portion of the transaction facilitating speech (e.g., the results including a new way for the user to pronounce the word "two hundred dollars" and therefore the pronunciation dictionary being updated to include the new pronunciation).

Referring again to Figure 8G, operation 805 may include operation 807, which depicts adding one or more words to a pronunciation dictionary as part of the adaptation data, the modification being based at least in part on the results of the first portion of the speech-facilitated transaction. For example, Figure 4 (e.g., Figure 4G) illustrates module 807 for adding one or more words to a pronunciation dictionary based at least in part on the results of obtaining a particular portion of the speech-facilitated transaction, the module 807 adding one or more words (e.g., the words "Atlanta, Georgia") to a pronunciation dictionary as part of the adaptation data, the modification being based at least in part on the results of the first portion of the speech-facilitated transaction (e.g., the results indicating that the target device (e.g., a personal navigation system) may not initially recognize the user's utterance of "Atlanta, Georgia," and therefore, the words and the user's pronunciation are added to the adaptation data).

Referring again to FIG8G , operation 805 may include operation 809 depicting adding one or more words to a pronunciation dictionary as part of the adaptation data, the modification being based at least in part on the results of a first portion of the speech-facilitated transaction, the first portion comprising one or more words pronounced by a particular party and corresponding pronunciations of the one or more words pronounced by the particular party, which are added to the pronunciation dictionary. For example, FIG4 (e.g., FIG4G ) illustrates module 809 for adding one or more words to a pronunciation dictionary based at least in part on the results of obtaining a particular portion of the speech-facilitated transaction comprising one or more words, the module 809 adding one or more words to a pronunciation dictionary as part of the adaptation data, the modification being based at least in part on the results of a first portion of the speech-facilitated transaction (e.g., the first portion being “enter PIN” for a transaction “withdraw two hundred dollars from a checking account”), the first portion comprising one or more words pronounced by a particular party (e.g., “four,” “seven,” and “three”), and corresponding pronunciations of the one or more words pronounced by the particular party (e.g., how a user pronounces the words “four,” “seven,” and “three”), which are added to the pronunciation dictionary.

Referring again to FIG8G , operation 805 may include operation 811, which describes replacing, in the adaptation data, a previous pronunciation dictionary that was part of the adaptation data and that was previously used to interpret the first portion of the speech-facilitated transaction with a new pronunciation dictionary. For example, FIG4 (e.g., FIG4G ) illustrates module 811 for replacing, based at least in part on the acquisition results of a particular portion of the speech-facilitated transaction, a previous pronunciation dictionary that was part of the adaptation data and that was previously used to interpret the first portion of the speech-facilitated transaction (e.g., the first portion of an order at an auto-pass window) with a new pronunciation dictionary.

Referring now to Figure 8H, operation 894 may include operation 813, which depicts modifying a path of the routing algorithm adapted to the data, the modification being based at least in part on the results of the first portion of the speech-facilitating transaction. For example, Figure 4 (e.g., Figure 4H) illustrates module 413 for applying a path of a routing algorithm that may be modified based at least in part on the results of obtaining a particular portion of the speech-facilitating transaction, wherein module 413 modifies a path of the routing algorithm adapted to the data, the modification being based at least in part on the results of the first portion of the speech-facilitating transaction (e.g., results indicating that the routing algorithm was successfully applied to the first portion of the user interacting with the motor vehicle control system).

Referring again to Figure 8H, operation 896 may include operation 815, which depicts sending updated adaptation data to the target device, the updated adaptation data being configured to be applied by the target device to interpret the second portion of the speech-facilitated transaction. For example, Figure 4 (e.g., Figure 4H) illustrates sending module 415 of revised speech adaptation data configured to interpret another portion of the speech-facilitated transaction, sending module 415 to a target device (e.g., an automated teller machine device) the updated adaptation data being configured to be applied by the target device (e.g., an automated teller machine device) to interpret the second portion (e.g., indicating the amount of money withdrawn) of the speech-facilitated transaction (e.g., withdrawing two hundred dollars from a savings account).

Referring again to Figure 8H, operation 896 may include operation 817, which depicts sending updated adaptation data to the target device, the updated adaptation data being configured to be applied by the target device to interpret the second portion of the speech-favored transaction, wherein no speech was interpreted between the first portion of the speech-favored transaction and the second portion of the speech-favored transaction. For example, Figure 4 (e.g., Figure 4H) shows a sending module 417 of modified speech adaptation data configured to be used to interpret another portion of the speech-favored transaction immediately after interpreting the particular portion, the sending module 417 sending updated adaptation data to the target device (e.g., a computer configured to receive speech input), the updated adaptation data being configured to be applied by the target device to interpret the second portion of the speech-favored transaction (e.g., the second segment of the dictation), wherein no speech was interpreted between the first portion of the speech-favored transaction (e.g., the first segment of the dictation) and the second portion of the speech-favored transaction.

8H , operation 896 may include operation 819, which depicts sending the updated adaptation data to the target device. For example, FIG4 (e.g., FIG4H ) illustrates a revised speech adaptation data sending module 419 that sends the updated adaptation data (e.g., an updated speech portion labeling algorithm) to the target device (e.g., a speech-enabled media player).

8H , operation 896 may include operation 821, which depicts receiving an indication from the target device that the updated adaptation data has been applied. For example, FIG. 4 (e.g., FIG. 4H ) illustrates receiving module 421 receiving an indication of revised speech adaptation data, the receiving module 421 receiving an indication (e.g., receiving a signal sent from the target device) from the target device (e.g., a speech-enabled media player) that the updated adaptation data has been applied (e.g., the updated adaptation data has replaced the adaptation data, or the existing adaptation data has been revised as instructed by the updated adaptation data).

Referring now to Figure 8I, operation 896 may include operation 823, which depicts sending the updated adaptation data to the target device. For example, Figure 4 (e.g., Figure 4I) illustrates a modified speech adaptation data sending module 423 that sends updated adaptation data (e.g., a set of proper noun pronunciations (e.g., city names) that have been modified based on the new user pronunciation) to a target device (e.g., a vehicle-based navigation system).

8I , operation 896 may include operation 825, which depicts receiving an indication from the target device that the updated adaptation data has been applied. For example, FIG4 (e.g., FIG4I ) illustrates receiving module 425 of an indication of applying modified speech adaptation data, which receives an indication from a target device (e.g., a vehicle-based navigation system) that updated adaptation data (e.g., a set of proper noun pronunciations (e.g., city names) that have been modified based on a new user pronunciation) has been applied (receiving data indicating successful application).

8I , operation 896 may include operation 827, which depicts facilitating presentation of an indication that the second portion of the speech-facilitated transaction is ready to occur. For example, FIG4 (e.g., FIG4I ) illustrates presentation module 427 indicating that another portion of the speech-facilitated transaction is ready to be completed, which facilitates presentation of an indication (e.g., a visual indication (e.g., a light on the device is activated) or an audible beep) indicating that the second portion of the speech-facilitated transaction is ready to occur (e.g., a user's cellular device beeps when the vehicle-based navigation system receives updated adaptation data).

8I , operation 827 may include operation 829, which depicts displaying a message on the screen of the particular device indicating that the second part of the speech-facilitated transaction is ready to occur. For example, FIG4 (e.g., FIG4I ) illustrates display module 429 of a message indicating that another part of the speech-facilitated transaction is ready to occur, which displays a message (e.g., “Now continue speaking”) on the screen of the particular device (e.g., a user's universal remote control) indicating that the second part of the speech-facilitated transaction (e.g., commanding a home theater system to play the movie “Inception”) is ready to occur.

Referring now to Figure 8I, operation 827 may include operation 831, which depicts facilitating display of a message on the screen of the target device indicating that the second portion of the speech-facilitated transaction is ready to occur. For example, Figure 4 (e.g., Figure 4I) illustrates facilitating module 431 displaying a message on the target device indicating that another portion of the speech-facilitated transaction is ready to occur. The facilitating module 431 facilitates displaying a message on the screen of the target device (e.g., sending a signal to the auto-pass window instructing the auto-pass window to display the words "Please Continue with Your Order") indicating that the second portion of the speech-facilitated transaction (e.g., a second order for a double bacon cheeseburger and fries) is ready to occur.

All of the foregoing U.S. patents, U.S. patent application publications, U.S. patent applications, foreign patents, foreign patent applications, and non-patent publications cited in this specification and/or listed in any Application Data Sheet are incorporated herein by reference to the extent not inconsistent with this application.

While particular aspects of the present subject matter described herein have been shown and described, it will be apparent to those skilled in the art that, based on the teachings herein, various changes and modifications may be made without departing from the subject matter described herein and its broader aspects, and, therefore, the appended claims are intended to cover within their scope all such changes and modifications as fall within the true spirit and scope of the subject matter described herein. Those skilled in the art will understand that, in general, the terms used herein (and particularly in the appended claims (e.g., in the body of the appended claims)) are generally intended to be interpreted as "open-ended" terms (e.g., the term "including" should be interpreted as "including but not limited to," the term "having" should be interpreted as "having at least...", the term "comprising" should be interpreted as "including but not limited to," etc.).

Those skilled in the art will further understand that if an introduced claim intends to refer to a particular number, such intent will be expressly set forth in the claim, and in the absence of such clarification, there is no such intent. For example, to aid in understanding, the claims appended below may contain the use of the introductory words "at least one" and "one or more" to introduce claim recitations. However, the use of these words should not be construed to imply that any particular claim recited by the indefinite article "a" or "an" will be limited to claims containing only one such recitation, even when the same claim includes the introductory words "one or more" or "at least one" and an indefinite article such as "a" or "an" (e.g., "a" and/or "an" should generally be construed to mean "at least one" or "one or more"); this is also true when definite articles are used to introduce claim recitations. In addition, even if a particular number of introductory claim references is explicitly recited, those skilled in the art will recognize that these references should generally be interpreted to mean at least the number of references (e.g., a simple reference to "two references" without other modifiers generally means at least two references, or two or more references).

In addition, in those cases where the conventional analogy of "at least one of A, B, and C, etc." is used, generally such interpretation is intended to convey that one skilled in the art would understand the convention (e.g., "a system having at least one of A, B, and C" would include but is not limited to systems having A alone, B alone, C alone, A and B together, A and C together, B and C together, and/or A, B, C together, etc.). In those cases where the conventional analogy of "at least one of A, B, or C" is used, generally such interpretation is intended to convey that one skilled in the art would understand the convention (e.g., "a system having at least one of A, B, or C" would include but is not limited to systems having A alone, B alone, C alone, A and B together, A and C together, B and C together, and/or A, B, C together, etc.). One skilled in the art would also understand that separators and/or words generally indicating two or more optional items (whether in the specification, claims, or drawings) should be understood to contemplate the possibility of including one, either, or both items, unless the context indicates otherwise. For example, the phrase "A or B" will generally be understood to include the possibilities of "A" or "B" or "A and B."

With respect to the appended claims, it will be understood by those skilled in the art that the operations recited herein may generally be performed in any order. In addition, although the various operational flows are presented in order, it will be understood that the operations may be performed in an order different from that shown, or may be performed simultaneously. Examples of these alternative sequences may include overlapping, interleaved, interrupted, reordered, incremental, preliminary, supplementary, simultaneous, reversed, or other variant sequences, unless the context indicates otherwise. Furthermore, terms such as "responsive to," "associated with," or other past tense adjectives are generally not intended to exclude such variations, unless the context indicates otherwise.

This application may refer to one or more trademarks, such as words, letters, characters, or devices adopted by a manufacturer or merchant to identify and/or distinguish his or her products from other products. Trademark names used herein are described in language that makes their identity clear, distinguishes them from common descriptive nouns, has a fixed and unambiguous meaning, or, in many (if not all) cases, is accompanied by other specialized designations using terms not covered by trademarks. In addition, trademark names described herein have meanings that are well known and defined in the literature, but do not refer to products or compounds to which knowledge of one or more trade secrets is required to give their meaning. All trademarks cited in this application are the property of their respective owners, and the appearance of one or more trademarks in this application does not diminish or otherwise adversely affect the validity of one or more trademarks. It is assumed that all trademarks appearing in this application (whether registered or unregistered) include the correct trademark marking, such as or bracketed capitalization (e.g., [trademark name]), even if such trademark marking does not explicitly appear immediately adjacent to the trademark. Whenever a trademark is used in a descriptive manner to refer to a product or process, the trademark should be interpreted as referring to the corresponding product or process as of the filing date of this application.

Those skilled in the art will understand that the foregoing specific exemplary processes and/or apparatus and/or techniques are representative of more general processes and/or apparatus and/or techniques taught elsewhere herein, such as in the claims filed with this application and/or in other parts of this application.

Claims (47)

1. A method for computation implementation, comprising: Manage adaptation data, wherein the adaptation data is associated with at least one aspect of a particular party’s speech; In response to an instruction to facilitate a speech-friendly transaction associated with a particular party, the adaptive data is transmitted to a target device, wherein the adaptive data is associated with at least one aspect of the speech of the particular party; and Determining whether to update the adaptation data, the determination being at least partially based on at least a portion of the results of the speech-favoring transactions, wherein the determination of whether to update the adaptation data, at least partially based on at least a portion of the results of the speech-favoring transactions, includes: Receive the results of the first part of the transaction that facilitates the speech; The adaptation data is updated at least in part based on the results of the first part of the transaction that facilitates speaking; and Before the end of the second part of the transaction that facilitates speaking, updated adaptation data is sent to the target device, the updated adaptation data being configured to be applied by the target device. 2. The computational implementation method of claim 1, wherein the management of adaptation data, wherein the adaptation data is associated with at least one aspect of a particular party's speech, comprises: Manage adaptation data, wherein the adaptation data is associated with at least one prior speech-favoring transaction made by the specific party. 3. The computational implementation method of claim 1, wherein the management of adaptation data, wherein the adaptation data is associated with at least one aspect of a particular party's speech, includes: Manage adaptive data, which includes data that associates the pronunciation of one or more phonemes made by the particular party with one or more concepts. 4. The computational implementation method of claim 1, wherein the management of adaptation data, wherein the adaptation data is associated with at least one aspect of a particular party's speech, comprises: To obtain a baseline for the location of the adapted data; and The location where the adaptation data is provided at specific intervals. 5. The computational implementation method of claim 1, wherein the management of adaptation data, wherein the adaptation data is associated with at least one aspect of a particular party's speech, comprises: To obtain a baseline for the location of the adapted data; and The location of the adaptation data is provided upon request. 6. The computational implementation method of claim 1, wherein the instruction to facilitate the transmission of the adaptive data to the target device in response to a transaction associated with a particular party's speech, wherein the adaptive data is associated with at least one aspect of the particular party's speech, includes: In response to an instruction to associate a speech-friendly transaction with a particular party, a pronunciation dictionary is sent to a target device, wherein the adaptation data is associated with at least one aspect of the speech of the particular party. 7. The computational implementation method of claim 1, wherein the instruction to facilitate the transmission of the adaptive data to the target device in response to a transaction associated with a particular party's speech, wherein the adaptive data is associated with at least one aspect of the particular party's speech, includes: In response to an instruction related to a speech-favorable transaction with a particular party, a set of instructions is sent to a target device to replace a word frequency table with a modified word frequency table that reflects the word usage of a particular user, wherein the adaptation data is associated with at least one aspect of the speech of the particular party. 8. The computational implementation method of claim 1, wherein the instruction to facilitate the transmission of the adaptive data to the target device in response to a transaction associated with a particular party's speech, wherein the adaptive data is associated with at least one aspect of the particular party's speech, includes: The adaptive data is facilitated to a target device in response to an instruction from a particular party to perform a transaction that facilitates the speech, wherein the adaptive data is associated with at least one aspect of the particular party. 9. The computational implementation method of claim 8, wherein the facilitation of transmitting the adaptive data to the target device is in response to an instruction from a particular party to perform a transaction that facilitates the speech, wherein the adaptive data is associated with at least one aspect of the particular party's speech, comprising: In response to receiving from the target device an instruction from the specific party to perform a transaction that facilitates the speech, the adaptive data is facilitated to be transmitted to the target device, wherein the adaptive data is associated with at least one aspect of the specific party's speech. 10. The computational implementation of the method of claim 9, wherein the facilitation of transmitting the adaptive data to the target device is in response to an instruction received from the particular device that a particular party intends to perform a transaction that facilitates the speech, wherein the adaptive data is associated with at least one aspect of the particular party's speech, comprising: The adaptive data is facilitated to the target device in response to an instruction from the specific party that it is speaking to the target device. 11. The computational implementation method of claim 8, wherein the facilitation of transmitting the adaptive data to a target device is initiated in response to an instruction from a particular party to perform a speech-facilitating transaction, wherein the adaptive data is associated with at least one aspect of the particular party's speech, comprising: The adaptive data is facilitated to a target device in response to an instruction received from a specific device associated with the specific party that the specific party intends to perform a transaction that facilitates the speech, wherein the adaptive data is associated with at least one aspect of the speech of the specific party. 12. The computational implementation method of claim 1, wherein the instruction to facilitate the transmission of the adaptive data to the target device in response to a transactional association with a particular party that facilitates speech includes: First adaptation data associated with a first aspect of the speech of the specific party is sent to the target device; and Before the transaction that facilitates the speech of the specific party ends, second adaptation data associated with the second aspect of the speech of the specific party is sent to the target device. 13. The computational implementation method of claim 12, wherein sending the first adaptation data associated with the first aspect of the speech of the particular party to the target device comprises: First adaptation data associated with the accent of the specific party is sent to the target device. 14. The computational implementation of the method of claim 12, wherein sending the first adaptation data associated with the first aspect of the speech of the particular party to the target device comprises: The first adaptation data is sent by a group of members who share at least one property with the specific party, based on previous transactions that facilitate the conversation. 15. The computational implementation method of claim 14, wherein sending first adaptation data based on a previous conversational transaction by a group of members having at least one property common to the particular party comprises: First adaptation data is sent by group members originating from the same geographical region as the specific party, based on previous transactions that facilitated the conversation. 16. The computational implementation method of claim 12, wherein sending the second adaptation data associated with the second aspect of the speech of the particular party to the target device before the conclusion of the transaction favorable to the speech of the particular party comprises: Before the transaction facilitating the speech of the specific party concludes, in response to a request from the target device, second adaptation data of the second aspect of the speech associated with the specific party is sent to the target device. 17. The computational implementation of the method of claim 1, wherein the determination of whether to update the adaptation data, based at least in part on at least a portion of the result of the speech-favoring transaction, comprises: The decision not to update the adaptation data is based at least in part on the results of at least a portion of the transactions that facilitate speaking. 18. The computational implementation of the method of claim 1, wherein the determination of whether to update the adaptation data, based at least in part on at least a portion of the result of the speech-favoring transaction, comprises: Determining whether to update the adaptation data, the determination is based at least in part on the results of the initial portion of the transaction that facilitates speaking. 19. The computational implementation of the method of claim 1, wherein the determination of whether to update the adaptation data, based at least in part on at least a portion of the result of the speech-favoring transaction, comprises: Determine whether to update the adaptation data, wherein the speech-favorable transactions include a first sentence and a second sentence, and the determination occurs after the first sentence and before the second sentence. 20. The computational implementation of the method of claim 1, wherein the determination of whether to update the adaptation data, based at least in part on at least a portion of the outcome of the speech-favoring transaction, comprises: Determine whether to update the adaptation data, and make the determination before the transaction that facilitates the speech ends. 21. The computational implementation method of claim 1, wherein the determination of whether to update the adaptation data, based at least in part on at least a portion of the outcome of the speech-favoring transaction, comprises: A determination is made as to whether to update the adaptation data, the determination being made after at least one word has been spoken in the speech-favoring transaction. 22. The computational implementation of the method of claim 21, wherein the determination of whether to update the adaptation data, made after at least one word is spoken in the speech-favorable transaction, comprises: A determination is made as to whether to update the adaptation data, and this determination occurs before a specific word is spoken in the speech-favoring transaction. 23. The computational implementation of the method of claim 1, wherein the determination of whether to update the adaptation data, based at least in part on at least a portion of the outcome of the speech-favoring transaction, comprises: Receive at least a portion of the results of the transaction that facilitates the speech, and determine whether to update the adaptation data, the determination being at least in part based on the received results. 24. The computational implementation of the method of claim 23, wherein receiving at least a portion of the result of the speech-facilitating transaction comprises: Receive at least a portion of the results of the transaction that facilitates the speech from the specific party. 25. The computational implementation of the method of claim 24, wherein receiving at least a portion of the result of the speech-facilitating transaction from the particular party comprises: The results of at least a portion of the conversation-facilitating transaction are received from the specific party interacting with the specific device, which is configured to manage the adaptation data. 26. The computational implementation of the method of claim 24, wherein receiving at least a portion of the speech-facilitating transaction from the specific party interacting with a specific device configured to manage the adaptive data comprises: After the transaction that facilitates speaking has concluded, at least a portion of the result of the transaction that facilitates speaking is received from the specific party that provided feedback to the specific device. 27. The computational implementation of the method of claim 23, wherein receiving at least a portion of the result of the speech-facilitating transaction comprises: Receiving at least a portion of the transaction that facilitates the speech is an indication that it was unsuccessful. 28. The computational implementation of the method of claim 27, wherein the indication that receiving at least a portion of the speech-facilitating transaction is unsuccessful includes: The recipient receives an indication that at least a portion of the transaction that facilitates speech is not successfully interpreted by the target device. 29. The computational implementation of the method of claim 23, wherein receiving at least a portion of the result of the speech-facilitating transaction comprises: The target device receives an indication that at least a portion of the conversation-facilitating transaction has been unsuccessful. 30. The computational implementation of the method of claim 29, wherein receiving at least a portion of the result of the speech-facilitating transaction comprises: The target device receives an indication that at least a portion of the transaction that facilitates speaking has a confidence rate below a specific threshold. 31. The computational implementation method of claim 23, wherein receiving at least a portion of the result of the speech-facilitating transaction comprises: Receive at least a portion of the results of the speech-facilitating transaction, the results including the pronunciation of one or more words spoken by the specific party during the speech-facilitating transaction. 32. The computational implementation method of claim 23, wherein receiving at least a portion of the result of the speech-facilitating transaction comprises: Receive at least a portion of the results of the speech-facilitating transaction, the results including a table of one or more words interpreted during the speech-facilitating transaction and the pronunciation of one or more words interpreted by the specific party. 33. The computational implementation method of claim 1, wherein the determination of whether to update the adaptation data, based at least in part on at least a portion of the results of the speech-favoring transactions, comprises: Receive at least a portion of the results of the transaction that facilitates the speech; The adaptation data is updated based on at least a portion of the results of the speech-favoring transactions; and Updated adaptation data is sent to the target device before the transaction that facilitates speaking ends. 34. The computational implementation method of claim 1, wherein the determination of whether to update the adaptation data, based at least in part on at least a portion of the outcome of the speech-favoring transaction, comprises: Receive at least a portion of the results of the transaction that facilitates the speech; and The adaptation data is updated based on at least a portion of the results of the transactions that facilitate speaking. 35. The computational implementation of the method of claim 1, wherein the determination of whether to update the adaptation data, based at least in part on at least a portion of the results of the speech-favoring transactions, comprises: Receive update data from another device regarding updating the adaptation data; and The adaptation data is updated based on the received updated data. 36. The computational implementation of the method of claim 1, wherein the determination of whether to update the adaptation data, based at least in part on at least a portion of the result of the speech-favoring transaction, comprises: Receive at least a portion of the results of the transaction that facilitates the speech; Send at least a portion of the results of the transaction that facilitates speaking to another location; and Updated data is received from the other location, the updated data including an indication of whether to update the adaptation data. 37. The computational implementation method of claim 36, wherein sending at least a portion of the result of the speech-facilitating transaction to another location comprises: At least a portion of the results of the transaction that facilitates speaking is sent to another location where the adaptation data is also stored. 38. The computational implementation of the method of claim 36, wherein receiving updated data including an indication of whether to update the adaptation data from the further location comprises: Update data is received from the other location, the update data further including instructions for updating the adaptation data. 39. The computational implementation of the method of claim 1, wherein the determination of whether to update the adaptation data, based at least in part on at least a portion of the result of the speech-favoring transaction, comprises: Receive at least a portion of the result of the speech-favoring transaction, wherein the result indicates that the speech-favoring transaction is moving too fast for the speech to be fully processed; and The video or audio instruction is presented to the specific party, indicating that the specific party should slow down the conversation-facilitating transaction. 40. The computational implementation of the method of claim 1, wherein updating the adaptation data based at least in part on the result of the first portion of the speech-favoring transaction comprises: The algorithm for adapting the data is modified, at least in part, based on the results of the first part of the transaction that facilitates speaking. 41. The computational implementation method of claim 40, wherein the algorithm for modifying the adaptation data based at least in part on the result of the first portion of the speech-favoring transaction comprises: At least one parameter of at least one algorithm for adapting the data is modified, at least in part, based on the results of the first part of the transaction that facilitates speaking. 42. The computational implementation method of claim 1, wherein updating the adaptation data based at least in part on the result of the first portion of the speech-favoring transaction comprises: The pronunciation dictionary, which is part of the adaptation data, is revised, and the revision is based at least in part on the results of the first part of the speech-facilitating transaction. 43. The computational implementation of the method of claim 42, wherein the correction of the pronunciation dictionary as part of the adaptation data, at least in part based on the result of the first portion of the speech-favoring transaction, comprises: One or more words are added to the pronunciation dictionary as part of the adaptation data, and the correction is based at least in part on the results of the first part of the speech-facilitating transaction. 44. The computational implementation of the method of claim 42, wherein the correction of the pronunciation dictionary as part of the adaptation data, at least in part based on the result of the first portion of the speech-favoring transaction, comprises: In the adaptation data, a new pronunciation dictionary replaces the previous pronunciation dictionary, which was part of the adaptation data and was applied when the first part of the speech-facilitating transaction was previously interpreted. 45. The computational implementation of the method of claim 1, wherein updating the adaptation data based at least in part on the result of the first portion of the speech-favoring transaction comprises: The path selection algorithm for the adapted data is modified, the modification being at least in part based on the results of the first part of the transaction that facilitates speaking. 46. A computationally implemented system, comprising: A device for managing adaptation data, wherein the adaptation data is associated with at least one aspect of a particular party’s speech; A means for facilitating the transmission of adaptive data to a target device in response to an instruction associated with a transaction that facilitates speech by a particular party, wherein the adaptive data is associated with at least one aspect of the speech of the particular party; A means for determining whether to update the adaptation data, the determination being based at least in part on the result of at least a portion of the speech-favoring transactions, wherein the determination of whether to update the adaptation data, based at least in part on the result of at least a portion of the speech-favoring transactions, includes: Receive the results of the first part of the transaction that facilitates the speech; The adaptation data is updated at least in part based on the results of the first part of the transaction that facilitates speaking; and Before the end of the second part of the transaction that facilitates speaking, updated adaptation data is sent to the target device, the updated adaptation data being configured to be applied by the target device. 47. A device defined by a computational language, comprising: One or more interconnected physical machines are ordered to manage adaptive data, wherein the adaptive data is associated with at least one aspect of a particular party’s speech; The adaptive data is sequenced to facilitate the transmission of the data to one or more interconnected physical machines of a target device in response to an instruction associated with a conversational transaction with a particular party, wherein the adaptive data is associated with at least one aspect of the conversation of the particular party; and One or more interconnected physical machines are ordered to determine whether to update the adaptation data, the determination being based at least in part on at least a portion of the outcome of the speech-favoring transactions, wherein the determination of whether to update the adaptation data, based at least in part on at least a portion of the outcome of the speech-favoring transactions, includes: Receive the results of the first part of the transaction that facilitates the speech; The adaptation data is updated at least in part based on the results of the first part of the transaction that facilitates speaking; and Before the end of the second part of the transaction that facilitates speaking, updated adaptation data is sent to the target device, the updated adaptation data being configured to be applied by the target device.