CN108257601A - For the method for speech recognition text, equipment, client terminal device and electronic equipment - Google Patents

Abstract

A method, device, client device and electronic device for voice recognition of text are disclosed. The method includes: receiving a voice input from a user; recognizing the voice input to provide at least two alternative associated words; receiving an instruction voice from the user; recognizing the instruction voice to obtain a voice instruction, wherein, The voice instruction is used to determine a target associated word in the at least two candidate associated words; and, based on the voice instruction, determine the target associated word as the recognized text. According to the present invention, the accuracy of speech recognition text can be improved.

Description

Method, device, client device and electronic device for speech recognition text

technical field

The present invention relates to the technical field of speech recognition, and more specifically, to a method, device, client device and electronic device for speech recognition text.

Background technique

As the hardware of the smart terminal continues to upgrade and the system continues to improve, it provides more and more means and methods for user interaction. In addition, with the explosive growth of mobile Internet usage, there are more and more scenarios where users use mobile applications (APP) to solve their daily needs.

Speech recognition technology is also more and more widely used in mobile phone applications. For example, many search engines, mobile browsers, e-commerce APPs, etc. can support the function of converting the voice entered by the user into text for searching.

In many languages, there are many words with the same or similar sound but different meanings. Especially in Chinese, the proportion of homonyms/approximate words is relatively high. In order to more accurately identify the word expected by the user from the set of homophones/approximate words, in the prior art, the usual solution is to select the most appropriate word as the recognized text based on the semantics of the user's complete segment displayed to the user. However, in many cases, prior art solutions are not effective. For example, when the user only enters a single word or the entered speech is segmented, the solutions in the prior art cannot identify words that meet the user's expectations from the homonym/approximate word set, and the accuracy of speech recognition is low.

Therefore, the inventor believes that it is necessary to improve the problems existing in the above-mentioned prior art.

Contents of the invention

An object of the present invention is to provide a technical solution for a method of speech recognition of text.

According to a first aspect of the present disclosure, there is provided a method for voice recognition of text, comprising: receiving a voice input from a user; recognizing the voice input to provide at least two alternative associated words; receiving a voice input from the user Instruction voice; identify the instruction voice to obtain a voice instruction, wherein the voice instruction is used to determine the target associated word in the at least two candidate associated words; and determine the target associated word based on the voice instruction as the recognized text.

Optionally, recognizing the speech input further includes: recognizing the speech input to obtain a speech fingerprint of the speech input, wherein the speech fingerprint is a pronunciation feature identifier associated with the speech input; querying a thesaurus of associated words to obtain at least two candidate associated words associated with the voice fingerprint; and displaying the at least two candidate associated words to a user.

Optionally, the method further includes: adjusting the position order of at least two candidate associated words associated with the voice fingerprint based on the determined target associated words.

Optionally, the instruction voice is a monosyllabic voice.

Optionally, the voice instructions are instructions within a limited set of instructions.

Optionally, the number of the candidate associated words is less than or equal to 10, each of the candidate associated words corresponds to one of the numbers 1-10, and the voice instruction is one of the numbers 1-10.

Optionally, receiving an instruction voice from the user further includes: receiving an instruction voice from the user, wherein the instruction voice includes multiple syllables and includes a single-syllable instruction voice, and wherein recognizing the instruction voice further includes : determining an instruction voice in the instruction voice; and recognizing the instruction voice based on a monosyllable manner to obtain a voice instruction.

Optionally, the method further includes: prompting the user to input an instruction voice when no instruction voice is received from the user within a predetermined time.

According to a second aspect of the present disclosure, there is provided an apparatus for speech recognition of text, comprising: means for receiving a speech input from a user; for recognizing the speech input to provide at least two alternative associated words A device for receiving an instruction voice from a user; a device for recognizing the instruction voice to obtain a voice instruction, wherein the voice instruction is used to determine the target in the at least two alternative associated words an associated word; and means for determining a target associated word as the recognized text based on the voice instruction.

According to a third aspect of the present disclosure, there is provided a client device, including the device for speech recognition text according to the embodiment, or designed to perform the operations in the method for speech recognition text according to the embodiment .

According to a fourth aspect of the present disclosure, there is provided an electronic device, including the client device according to the embodiment, or including a memory and a processor, wherein the memory stores executable instructions, and the executable instructions are stored in the electronic device. When the device runs, the processor is controlled to execute the operations in the method for speech recognition text according to the embodiment.

According to an embodiment of the present disclosure, the accuracy of speech recognition text can be improved.

Other features of the present invention and advantages thereof will become apparent from the following detailed description of exemplary embodiments of the present invention with reference to the accompanying drawings.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention.

Fig. 1 shows a schematic flowchart of a method according to an embodiment of the present disclosure.

FIG. 2 shows a schematic flowchart of a method according to an example of step 1200 of the present disclosure.

Fig. 3 shows a schematic block diagram of a client device according to another embodiment of the present disclosure;

Fig. 4 shows a schematic block diagram of an electronic device according to another embodiment of the present disclosure;

5a to 5b show schematic diagrams of a display interface according to an example of an embodiment of the present disclosure.

Detailed ways

Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that the relative arrangements of components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

The following description of at least one exemplary embodiment is merely illustrative in nature and in no way taken as limiting the invention, its application or uses.

Techniques, methods and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, such techniques, methods and devices should be considered part of the description.

In all examples shown and discussed herein, any specific values should be construed as exemplary only, and not as limitations. Therefore, other instances of the exemplary embodiment may have different values.

It should be noted that like numerals and letters denote like items in the following figures, therefore, once an item is defined in one figure, it does not require further discussion in subsequent figures.

Hereinafter, various embodiments and examples according to the present disclosure are described with reference to the accompanying drawings.

<method>

Fig. 1 shows a schematic flowchart of a method according to an embodiment of the present disclosure.

As shown in FIG. 1, at step 1100, voice input from a user is received.

For example, a client device (client application) having a speech recognition function receives an interactive operation from a user to enter an interactive interface for speech recognition, and receives the user's voice input on the interactive interface.

Step 1200, recognize the speech input to provide at least two candidate associated words.

For example, alternative associated words refer to words with the same phonetic fingerprint, and may be pre-stored in the associated word lexicon. Speech fingerprint is the pronunciation feature identification of words. For example, for Chinese (a Mandarin family), the pinyin of a word can be used as a phonetic fingerprint. For example, an example of a voice fingerprint is "jianpu". In the Mandarin family, words associated with the phonetic fingerprint may include the following words: numbered notation, simple, frugal, and so on.

In an example, the step S1200 may be implemented in a manner as shown in FIG. 2 .

As shown in FIG. 2, in step 1201, the voice input is recognized to obtain a voice fingerprint of the voice input.

The voice fingerprint is an identification of pronunciation features associated with the voice input. For example, the pronunciation feature identifier associated with the speech input is the pinyin of the speech input, which can be used as the recognized speech fingerprint.

Step 1202, query the associated word thesaurus to obtain at least two candidate associated words associated with the voice fingerprint.

For example, in the associated word thesaurus, multiple associated words corresponding to voice fingerprints may be stored in the form of a list. In the initial state of the associated word thesaurus, the order of words can be sorted from high to low according to the frequency of use of words in daily social communication, wherein the words with high frequency of use are placed first. The order of the associated words in the list can be used as the order of position when displayed. For example, if the position of the candidate associated word is the first in the list, when displayed to the user, the number corresponding to the candidate associated word is "1".

After the voice fingerprint of the voice input is obtained, if there are at least two associated words corresponding to the voice fingerprint in the associated word lexicon, the at least two associated words are used as candidate associated words. Those skilled in the art should understand that if there is only one candidate associated word associated with the voice fingerprint in the associated word lexicon, the candidate associated word can be directly used as the speech recognition text.

Step 1203, displaying the at least two candidate associated words to the user.

Here, the number of displayed alternative associated words can be set to be less than or equal to 10. If the number of alternative associated words in the associated word thesaurus is greater than 10, only the first 10 words are selected as alternative associated words when displayed.

When at least two candidate associated words are displayed, each candidate associated word corresponds to a number in numbers 1-10, so that the user selects the target associated word by inputting an instruction voice.

The advantage of this approach is that, generally, in various languages, especially in Chinese, numbers 1-10 are all monosyllabic and/or easy to recognize. Therefore, limiting the number of candidate associated words can improve the recognition accuracy when the user selects the candidate associated words.

In addition, when the number of alternative associated words is greater than 10, a separate specific word, such as "next page", can be set, and the replacement of the alternative associated words can be realized through this specific word. The user can select a desired word among the replaced candidate associated words.

After at least two candidate associated words are displayed to the user, enter step 1300, and receive an instruction voice from the user.

Here, the numbers 1-10 are monosyllabic, and the recognition rate of the numbers is very high, which can ensure the high accuracy of command voice recognition. In this example, the command voice is defined as a monosyllabic voice. In addition, the voice command is an command within a limited set of commands, for example, the command voice from the user is one of numbers 1-10.

For example, the voice fingerprint recognized according to the voice input from the user is "jingzhi", and the alternative associated words associated with "jingzhi" displayed to the user are "1. Stillness", "2. Delicacy", and "3. Net worth" , "4. Refined". If the user selects "exquisite" as the target associated word, then enter "2" as the voice command.

In an example, receiving an instruction voice from the user may further include: receiving an instruction voice from the user, wherein the instruction voice includes multiple syllables and includes a single-syllable voice instruction voice.

For example, if the user selects the displayed second word as the target associated word, the user can enter the instruction voice "the second word", which includes multiple syllables and includes the monosyllable instruction voice "2".

This method of inputting instruction voice may be more in line with the user's habits in practical applications, which can not only enhance the user's experience, but also ensure the accuracy and convenience of instruction recognition.

In another example, if no instruction voice is received from the user within a predetermined time, the user may be prompted to input the instruction voice.

Specifically, a countdown of a predetermined time may be displayed while at least two candidate associated words are displayed, so as to prompt the user to input an instruction voice before the countdown ends. Optionally, when the predetermined time is reached, prompt information may be displayed to prompt the user to input an instruction voice.

In step 1400, the instruction voice is recognized to obtain a voice instruction, wherein the voice instruction is used to determine a target associated word among the at least two candidate associated words.

In one example, the command voice entered by the user is a monosyllable voice, and the voice command can be obtained directly by recognizing the command voice. For example, for the alternative associated words "1. Stillness", "2. Refined", "3. Net worth", and "4. Refined", assuming that the command voice entered by the user is "1", the voice command obtained by recognizing the command voice That is "1".

In another example, what the user enters is an instruction voice, and correspondingly, recognizing the instruction voice may also include: determining the instruction voice in the instruction voice; and recognizing the instruction voice based on a monosyllable manner to obtain the voice instruction.

For example, for the alternative associated words "1. static", "2. exquisite", "3. net value", "4. refined", the instruction voice entered by the user is "the first word", and the instruction voice in the instruction voice is determined "1", the instruction voice is recognized based on the monosyllable method, and the obtained voice instruction is "1".

In practical applications, after the target associated word is determined, the determined target associated word can also be displayed in color, so that it can be distinguished from other alternative associated words in color, so as to identify the word as the selected word.

It can be understood that if no voice command is recognized in this step, the user is prompted that the current recognition is invalid, and the user can choose to re-enter the voice or complete the current voice recognition.

Step 1500, determine target related words as the recognized text based on the voice instruction.

The candidate associated word corresponding to the voice instruction is determined as the target associated word. The target link is text recognized based on the user's speech input. For example, for the alternative associated words "1. still", "2. refined", "3. net worth", "4. refined", if the voice command is "1", the corresponding "stationary" is recognized based on the user's voice input of the text.

In an example, after the target associated word is determined based on the voice instruction, the positions of at least two candidate associated words associated with the voice fingerprint may be adjusted based on the determined target associated word. For example, the target associated word can be placed in the first position of at least two alternative associated words associated with the voice fingerprint, and the order of the alternative associated words can be adjusted by using the user's selection result, so as to improve the accuracy of recommendation in the next recognition, and improve user experience.

In this embodiment, based on the command voice actively input by the user, the text recognized from the homonym/approximate phonetic word set that meets the user's expectations can be corrected to improve the accuracy of the speech recognition text.

<device>

Those skilled in the art should understand that, in the field of electronic technology, the above methods can be embodied in products through software, hardware, or a combination of software and hardware. Those skilled in the art can easily generate a method for An apparatus for speech recognition of text, the apparatus includes means for performing various operations in the method for speech recognition of text according to the above-mentioned embodiments. For example, the device includes: means for receiving voice input from the user; means for recognizing the voice input to provide at least two alternative associated words; means for receiving instruction voice from the user; A device for recognizing the instruction voice to obtain a voice instruction, wherein the voice instruction is used to determine the target associated word in the at least two candidate associated words; and is used to determine the target associated word as the target associated word based on the voice instruction. A device for recognizing text.

<client device>

At least one embodiment according to the present disclosure can be implemented in a client device (or client application) such as a browser, WeChat, Weibo, and the like.

Fig. 3 shows a schematic block diagram of a client device according to another embodiment of the present disclosure. As shown in FIG. 3 , the client device 3000 includes a speech recognition text device 3010 . The speech recognition text device 3010 may be the device for speech recognition text according to the above-mentioned embodiments.

In addition, as mentioned above, a client device can also be generated based on the method described above, which can be designed to execute the steps in the solution of the embodiment described with reference to FIG. 1 .

Those skilled in the art know that, with the development of electronic information technology such as large-scale integrated circuit technology and the trend of software and hardware, it has become difficult to clearly divide the boundaries between software and hardware of computer systems. Because any operation can be realized by software or by hardware. Execution of any instruction can be done by hardware as well as by software. Whether to adopt a hardware implementation scheme or a software implementation scheme for a certain machine function depends on non-technical factors such as price, speed, reliability, storage capacity, and change cycle. For technical personnel, the software implementation manner and the hardware implementation manner are equivalent. Technicians can choose software or hardware according to needs to implement the above solution. Therefore, there is no limitation to specific software or hardware.

<electronic device>

Any of the above-described embodiments may be implemented in an electronic device such as a mobile phone, a tablet, or the like. For example, the electronic device may include the device for speech recognition text in the above embodiments or include the client device in the above embodiments.

In addition, FIG. 4 shows a schematic block diagram of an electronic device according to another embodiment of the present disclosure. As shown in FIG. 4, the electronic device 4000 may include a processor 4010, a memory 4020, an interface device 4030, a communication device 4040, a display device 4050, an input device 4060, a speaker 4070, a microphone 4080, and the like.

The processor 4010 may be, for example, a central processing unit (CPU), a microprocessor (MCU), and the like. The memory 4020 includes, for example, ROM (Read Only Memory), RAM (Random Access Memory), nonvolatile memory such as a hard disk, and the like. The interface device 4030 includes, for example, a USB interface, an earphone interface, and the like.

The communication device 4040 is capable of wired or wireless communication, for example.

The display device 4050 is, for example, a liquid crystal display, a touch display, and the like. The input device 4060 may include, for example, a touch screen, a keyboard, and the like. A user can input/output voice information through the speaker 4070 and the microphone 4080 .

The electronic device shown in Figure 4 is illustrative only and in no way intended to limit the invention, its application or uses.

In this embodiment, the memory 4020 is used to store instructions, and the instructions control the processor 4010 to perform operations in the method for speech recognition of text described above with reference to FIG. 1 when the electronic device 4000 is running. . Those skilled in the art should understand that although multiple devices are shown in FIG. 4 , the present invention may only involve some of them, for example, the processor 4010 and the storage device 4020 . A skilled person can design instructions according to the solutions disclosed in the present invention. How the instructions control the processor to operate is well known in the art, so it will not be described in detail here.

<example>

5a to 5b show schematic diagrams of a display interface according to an example of an embodiment of the present disclosure.

In this example, the speech recognition interactive interface of the browser is taken as an example for description.

The user enters the voice recognition interaction interface through an interactive operation with the display interface of the browser. As shown in FIG. 5 a , a prompt such as "Listening" may be displayed on the voice recognition interaction interface to prompt the user that voice can be input currently.

After entering the voice recognition interaction interface, the voice input from the user is received, and the voice fingerprint of the voice input is recognized. Next, query whether there are candidate associated words associated with the voice fingerprint in the associated word lexicon.

If it is found that there is one candidate associated word associated with the voice fingerprint in the associated word thesaurus, the candidate associated word is determined as the recognized text and displayed on the speech recognition interface. If it is found that the number of alternative associated words associated with voice fingerprints that exists in the associated word lexicon is at least two, the at least two alternative associated words are displayed in order on the voice recognition interface, and each alternative associated word is associated with a number Corresponds to a number from 1-10.

For example, the recognized voice fingerprint is "jianpu", and there are three candidate associated words associated with "jianpu" in the associated word lexicon: "simplified musical notation", "simple" and "simple". These three candidate associated words are displayed on the voice recognition interface in the order of words, and each candidate associated word corresponds to a number in 1-10. As shown in Figure 5b, the voice recognition interface displays: "1. Numbered musical notation", "2. Simple" and "3. Simple".

When at least three alternative associated words are displayed on the voice recognition interactive interface, a countdown may also be displayed at the same time to prompt the user to input an instruction voice. The command voice may be a monosyllabic voice entered by the user, or an instruction voice entered by the user, the instruction voice including multiple syllables and including a single-syllable voice.

Receive the command voice input by the user within the countdown time. If the user enters a correct and valid monosyllabic instruction within the countdown period, that is, the recognized voice instruction is a number, and the number is not greater than the number of currently displayed alternative associated words, the alternative associated words corresponding to the voice instruction will be determined is the target linker, as the recognized text. Optionally, the target associated word may be displayed in a color-changing manner, so that the display color of the target associated word is different from that of other candidate associated words, so as to identify it as a selected word.

If the user does not enter an instruction voice within the countdown period, or if the user enters a non-digit voice instruction, the user will be prompted that the speech recognition is invalid this time. The user can choose to re-enter the voice or complete this voice recognition.

If the user chooses to re-enter the voice, the voice recognition interface may display, for example, "Listening" to prompt the user to input the voice. If the user chooses to complete the speech recognition, the speech recognition interaction interface will be exited.

In this example, based on the instruction voice actively input by the user, it is possible to modify the text that meets the user's expectations from the set of homonyms/approximate words, so as to improve the accuracy of the speech recognition text.

The invention can be an apparatus, method and/or computer program product. A computer program product may include a computer readable storage medium having computer readable program instructions thereon for causing a processor to implement various aspects of the present invention.

A computer readable storage medium may be a tangible device that can retain and store instructions for use by an instruction execution device. A computer readable storage medium may be, for example, but is not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or flash memory), static random access memory (SRAM), compact disc read only memory (CD-ROM), digital versatile disc (DVD), memory stick, floppy disk, mechanically encoded device, such as a printer with instructions stored thereon A hole card or a raised structure in a groove, and any suitable combination of the above. As used herein, computer-readable storage media are not to be construed as transient signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., pulses of light through fiber optic cables), or transmitted electrical signals.

Computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or downloaded to an external computer or external storage device over a network, such as the Internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge servers. A network adapter card or a network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing/processing device .

Computer program instructions for carrying out operations of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or Source or object code written in any combination, including object-oriented programming languages—such as Smalltalk, C++, etc., and conventional procedural programming languages—such as the “C” language or similar programming languages. Computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server implement. In cases involving a remote computer, the remote computer can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as via the Internet using an Internet service provider). connect). In some embodiments, an electronic circuit, such as a programmable logic circuit, field programmable gate array (FPGA), or programmable logic array (PLA), can be customized by utilizing state information of computer-readable program instructions, which can Various aspects of the invention are implemented by executing computer readable program instructions.

Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It should be understood that each block of the flowcharts and/or block diagrams, and combinations of blocks in the flowcharts and/or block diagrams, can be implemented by computer-readable program instructions.

These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine such that when executed by the processor of the computer or other programmable data processing apparatus , producing an apparatus for realizing the functions/actions specified in one or more blocks in the flowchart and/or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause computers, programmable data processing devices and/or other devices to work in a specific way, so that the computer-readable medium storing instructions includes An article of manufacture comprising instructions for implementing various aspects of the functions/acts specified in one or more blocks in flowcharts and/or block diagrams.

It is also possible to load computer-readable program instructions into a computer, other programmable data processing device, or other equipment, so that a series of operational steps are performed on the computer, other programmable data processing device, or other equipment to produce a computer-implemented process , so that instructions executed on computers, other programmable data processing devices, or other devices implement the functions/actions specified in one or more blocks in the flowcharts and/or block diagrams.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, a portion of a program segment, or an instruction that includes one or more Executable instructions. In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented by a dedicated hardware-based system that performs the specified function or action , or may be implemented by a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that implementation by means of hardware, implementation by means of software, and implementation by a combination of software and hardware are all equivalent.

Having described various embodiments of the present invention, the foregoing description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and alterations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principle of each embodiment, practical application or technical improvement in the market, or to enable other ordinary skilled in the art to understand each embodiment disclosed herein. The scope of the invention is defined by the appended claims.

Claims (11)

1. a kind of method for speech recognition text, including：

Receive phonetic entry from the user；

The phonetic entry is identified, to provide at least two alternative conjunctive words；

Receive instruction voice from the user；

Described instruction voice is identified, to obtain phonetic order, wherein, the phonetic order is for determining described at least two Target association word in a alternative conjunctive word；And

Target association word is determined based on the phonetic order, as the text identified.

2. according to the method described in claim 1, wherein, the phonetic entry is identified and is further included：

The phonetic entry is identified, to obtain the voice fingerprint of the phonetic entry, wherein, the voice fingerprint is and institute Predicate sound inputs associated pronunciation character mark；

Conjunctive word dictionary is inquired to obtain at least two alternative conjunctive word associated with the voice fingerprint；And

Described at least two alternative conjunctive words are shown to user.

3. it according to the method described in claim 2, further includes：

Based on identified target association word, the position of at least two alternative conjunctive word associated with the voice fingerprint is adjusted Sequentially.

4. according to the method described in claim 1, wherein, described instruction voice is single syllable voice.

5. according to the method described in claim 4, wherein, the phonetic order is the instruction in limited instruction set.

6. according to the method described in claim 5, wherein, the quantity of the alternative conjunctive word is less than or equal to 10, each alternative pass Connection word with one in number 1-10 digital corresponding and described phonetic order is in digital 1-10 one.

7. it according to the method described in claim 4, wherein, receives instruction voice from the user and further includes：Receive the finger of user Show voice, wherein, the instruction voice include multiple syllables and instruction voice including single syllable voice and

Wherein, described instruction voice is identified and further included：

Determine the instruction voice in the instruction voice；And

Described instruction voice is identified based on monosyllabic mode, to obtain phonetic order.

8. it according to the method described in claim 1, further includes：

When being not received by instruction voice from the user in the given time, user input instruction voice is prompted.

9. a kind of equipment for speech recognition text, including：

For receiving the device of phonetic entry from the user；

For the phonetic entry being identified the device to provide at least two alternative conjunctive words；

For receiving the device of instruction voice from the user；

For being identified described instruction voice to obtain the device of phonetic order, wherein, the phonetic order is used to determine Target association word in at least two alternative conjunctive word；And

For determining device of the target association word as the text identified based on the phonetic order.

10. a kind of client terminal device including the equipment according to claim 9 for speech recognition text or is set Count into the operation for performing in the method for speech recognition text described in any one in claim 1-8.

11. a kind of electronic equipment, including client terminal device according to claim 10 or including memory and processing Device, wherein, the memory stores executable instruction, and the executable instruction controls the place when the electronic equipment is run Manage the operation in the method for speech recognition text described in any one of the device execution in claim 1-8.