WO2004029930A1 - Voice recognition device, control device and method for computer-assisted completion of an electronic dictionary for a voice recognition device - Google Patents

Abstract

According to the invention, the similarity between a first utterance, before it is used in an electronic dictionary for a voice recognition unit to enable voice recognition, and at least one second utterance is determined in an utterance comparison area. The electronic dictionary is completed according to the determined similarities between the first utterance and at least the second utterance.

Description

description

Speech recognition device, control device and method for computer-aided supplementing of an electronic dictionary for a speech recognition device

The invention relates to a speech recognition device, a control device and a method for computer-aided addition of an electronic dictionary for a speech recognition device.

Within the framework of speech recognition, two different methods are usually distinguished, the so-called speaker-dependent speech recognition and the so-called speaker-independent speech recognition.

In particular in a speech recognition application in which the speech recognition device is embedded in the form of an embedded system in a low-computing environment, there is usually a unit for the speaker-independent

Speech recognition and a separate unit for speaker-dependent speech recognition are provided.

Hidden Markov models are usually used for speaker-independent speech recognition, for which

Recognition of speaker-dependent utterances usually a speech recognition device based on the principle of DTW (Dynamic Time Warping).

Speech recognition generally follows in such a way that a spoken speech signal is broken down into a sequence of spoken units, in other words, is mapped onto these. The sequence of spoken units, usually a sequence of phonemes, is compared with previously stored phoneme sequences, which represent reference utterances and are stored in an electronic dictionary. Is the phoneme sequence of the speech signal sufficiently similar to a reference utterance in the electronic dictionary, the spoken voice signal is recognized as representing the reference utterance and the reference utterance is output to the user as a speech recognition result.

In some applications, it is advantageous to make the electronic dictionary flexibly expandable, in other words, it is desirable to be able to add a reference utterance to the electronic dictionary, to change a reference utterance stored in the dictionary, or to change a reference utterance stored in the dictionary delete electronic dictionary.

For this purpose, it is known in the prior art to set up the electronic dictionary as an electronic file into which new reference statements can be written if a user has the appropriate access rights to the electronic file

Dictionary owns.

A disadvantage of the known procedure is in particular that the management of the electronic dictionary takes place in an uncontrolled manner and, for this reason, the size of the electronic dictionary can fundamentally increase without restriction, which leads to a considerable deterioration in the recognition performance of the speech recognition device and to an increased storage space requirement for storing the electronic dictionary can.

Furthermore, in a conventional speech recognition application in which both a speech recognition process for speaker-dependent speech recognition and a speech recognition process for speaker-independent speech recognition are provided, the speaker-independent and speaker-dependent speech recognition in to carry out speech recognition states which are logically completely separate from one another, the speaker-dependent and speaker-independent speech recognition being carried out by different speech recognition units.

An example of this can be seen in automatic speech recognition in the context of a telephone application, in which, for example, a predefined speaker-independent command “call” is stored as part of speech recognition using hidden Markov models. This means that a method for speaker-independent speech recognition is used to recognize this command becomes.

A DTW speech recognition unit is usually used to recognize dynamically expandable entries in a user-definable electronic dictionary, for example an electronic telephone book, in which electronic dictionary, for example, a name of a subscriber spoken by a user can be stored.

In this context it should be noted that in the scenario described above due to the fact that the speech recognition units on different

Based on speech recognition principles and speech recognition algorithms, different files are also provided for storing the respective electronic dictionaries used for speech recognition.

Foundations of hidden Markov models and thus of speaker-independent speech recognition can be found in [1]. Furthermore, in [1] basics about dynamic time warping, in other words about so-called dynamic time distortion, are described. In [1] there are also basics about the Viterbi algorithm and the training of hidden Markov models are described using a Viterbi algorithm.

Switching between different speech recognition devices, in particular loading a new electronic dictionary used for the respective speech recognition process and initializing the respective speech recognizer are very time-consuming. Speech recognition according to the prior art for a user utterance which contains both speaker-dependent and speaker-independent partial utterances is therefore very user-unfriendly.

Furthermore, the additional costs for the development as well as the storage and the acquisition of two mutually different speech recognition devices are considerable.

[2] describes a method and a device for speech recognition, in which a vocabulary is added a new word spoken by a user as a phoneme sequence, the phoneme sequence being formed from speaker-independent phonemes.

[3] describes a method in which a feature extraction is carried out for a spoken-in speech signal and a sequence of hidden Markov models, each representing a phoneme, is formed for the feature vectors formed therefrom, so that a word model is generated which contains the spoken-in speech signal best represented. The word model is stored as a new word to be recognized in a memory of the recognition device, ie clearly in an electronic dictionary, so that it can be used as a reference word for the speech recognition in a recognition mode of the speech recognition device. The invention is based on the problem of managing an electronic dictionary in a manner, in particular to add new reference statements, which ensures an improved recognition rate in the context of speech recognition using the electronic dictionary.

The problem is solved by the speech recognition device, by the control device and by the method for computer-aided addition of an electronic dictionary for a speech recognition device for speech recognition with the features according to the independent patent claims.

The speech recognition device has at least one speech recognition unit, which is preferably set up for speaker-independent speech recognition.

According to one embodiment of the invention, a plurality of speech recognition units, for example a speech recognition unit for speaker-independent speech recognition and a speech recognition unit for speaker-dependent speech recognition, can be provided. In principle, any number of speech recognition units can be provided, which use one or more electronic dictionaries according to the invention for speech recognition.

Furthermore, the speech recognition device has an electronic dictionary coupled to the speech recognition unit, in which the words taken into account in the context of the speech recognition are stored.

A word spacing determination unit is provided for determining the similarity of a first utterance to at least one second utterance in an utterance comparison space. Furthermore, a dictionary supplement unit is provided for supplementing the electronic dictionary with the first utterance, the supplementing the electronic Dictionary depends on the determined similarity of the first utterance with at least the second utterance.

A control device for controlling a technical system has a speech recognition device as described above, the control commands provided for controlling the technical system for speech recognition being stored in the electronic dictionary.

In a method for the computer-aided addition of an electronic dictionary for a speech recognition unit for speech recognition, in which the words taken into account in the context of speech recognition are stored, the similarity to at least one second utterance is determined in an utterance comparison space. The electronic dictionary is supplemented by the first utterance depending on the determined similarity of the first utterance with at least the second utterance.

Clearly, according to the invention, a first utterance, which is preferably spoken by a user and is present, for example, in the form of a sequence of phonemes formed from an analog speech signal, is checked to determine whether it meets one or more similarity criteria for one or more other utterances. The first utterance is only added to the electronic dictionary if the first utterance meets the similarity criterion. Otherwise the request to add the first utterance to the dictionary will be rejected and the first utterance will be rejected.

In this way, it is achieved that an electronic dictionary used in the context of speech recognition is only supplemented with a new entry if it is ensured that the similarity criterion is met; in other words, an entry in. Can only be achieved in this way the electronic dictionary is made when the Speech recognition performance, that is to say the recognition rate in the context of speech recognition using the supplemented electronic dictionary is not reduced or is reduced only to an acceptable extent represented by the similarity criterion.

Preferred developments of the invention result from the dependent claims.

The embodiments of the invention described below relate both to the speech recognition device, the control device and the method for the computer-aided addition of an electronic dictionary.

The word similarity determination unit of the

Speech recognition device can have a dictionary similarity determination unit with which the similarity of the first utterance to the second utterance is determined.

In this case, the second utterance is stored in the electronic dictionary. The speech recognition device, preferably the dictionary supplement unit, but alternatively to the word spacing determination unit, is set up in such a way that the first utterance is only added to the electronic dictionary if the

Similarity of the first utterance to the second utterance is less than a predetermined first similarity value.

This procedure clearly means that the first utterance is only added to the electronic dictionary if the distance value formed in the utterance comparison space, which describes the distance between the feature vectors representing the first utterance to the feature vectors representing the second utterance, is greater than one predefined similarity threshold. In other words, this procedure means that for an utterance before it is stored in the electronic dictionary, it is first checked whether the distance to the reference utterances previously stored in the electronic dictionary is sufficiently large.

According to another embodiment of the invention, it is provided that the word similarity determination unit has an utterance similarity determination unit for determining the similarity of the first utterance to a third utterance. The speech recognition device, preferably the dictionary supplement unit, alternatively the word spacing determination unit, is set up in such a way that the first utterance is only added to the electronic dictionary if the similarity of the first utterance to the third utterance is greater than a predetermined second similarity threshold.

Described clearly, this procedure means in particular if the same is spoken several times

Speech by a user that the spoken utterances are compared with each other and that an utterance can only be added to the electronic dictionary if several utterances are sufficiently similar to one another, so that the first utterance is selected as a representative of the multiple utterances of the same speech utterances and for this is then checked whether the distance to the stored reference utterances in the dictionary is sufficiently large.

This embodiment of the invention clearly represents a two-step procedure, whereby on the one hand it is achieved that the smallest possible number of new utterances is guaranteed in the case of unequal acoustic speech utterances, but the highest possible number of ones

Additions to the electronic dictionary, that is, entry assumptions with the same acoustic speech is achieved. Furthermore, the procedure described above achieves the lowest possible number of additional acoustic additions with the highest possible speech recognition rate of a speech recognition device using the supplemented electronic dictionary.

According to another embodiment of the invention, the speech recognition unit is set up for speaker-independent speech recognition.

Furthermore, a speech signal mapping unit coupled to the electronic dictionary can be provided for mapping the speech signal spoken by a user onto a sequence of spoken units which represents the speech signal.

The sequence of spoken units is preferably set up in such a way that it can be processed by the speech recognition unit as part of the speaker-independent speech recognition, the sequence of spoken units representing the first utterance.

The speech signal can be spoken into the speech recognition device by a user at the beginning of the method, but can alternatively already be stored in a purely analog or analog-digitized form as a speech signal and can be fed to the computer, for example, via a telecommunications network. The voice signals can also alternatively be stored in the memory of the speech recognition device, in which case the formation of the sequence of spoken units is based on the signals already stored in the memory.

The speech recognition unit can be set up for speaker-independent speech recognition based on Hidden Markov models, which are each trained on one predefined utterance stored in an electronic dictionary, for example a word and a sequence of words.

The speech recognition unit can alternatively be designed for speaker-independent speech recognition by means of statistical classifiers which are trained in a corresponding manner for speaker-independent speech recognition using an electronic dictionary with the utterances intended for speech recognition. For example, methods using artificial neural networks can be used as statistical classifiers.

The sequence of speech units is preferably formed by a phoneme chain, alternatively by means of a sequence of syllables, letters or a sequence of other speech units that are suitable for speech recognition.

The use of phonemes as loudspeaker units enables the use of units known per se in the context of speech recognition for the formation of phonemes from speech signals

Speech recognition device can be implemented inexpensively.

The invention can clearly be seen in the fact that by using a statistical method for parameter optimization, the above-described requirements for supplementing an electronic dictionary are found to be a sensible, optimized compromise.

In addition, predictions regarding the recognition quality, that is to say the achievable recognition rate with a fixed number of entries in the electronic dictionary, are possible. In other words, the quality of the speech recognition device is scalable.

According to the invention, speaker-dependent and speaker-independent vocabularies can be combined to form an overall vocabulary. If command words are present in a speaker-dependent part of the total vocabulary of words which activate control functions of a technical system to be controlled, their function is not impaired by new entries, since it is guaranteed that the similarity of a new word to the command words is sufficiently low so that a corresponding influencing is avoided.

The use of similarity measures or distance measures as threshold parameters, more clearly than that

Similarity thresholds allow the use of statistical methods, which are explained in more detail below, which can determine the optimal working range of the speech recognition device for a fixed number of entries.

The entry of a preferably speaker-dependent entry in the electronic dictionary is thus preferably implemented using a two-stage process.

In the first stage, a candidate, that is to say a speech that is to be stored in the electronic dictionary, is spoken NR _e p _ea times. Using the speech recognition device, each of the NR _e p _ea t statements on a respective sequence of spoken language

Units, preferably a sequence of phonemes. The sequence of language units created by the combination of the recognized speech-language units is also referred to below as a symbol chain.

Only if all NR _epea symbol chains of the respective current speech are a sufficiently short distance or, otherwise expressed, that they are sufficiently similar to one another, there is a "candidate for entry" at all.

If this is not the case, the request for the entry of the utterance in the electronic dictionary is rejected.

However, the attempt can be repeated any number of times.

The second level is used to determine the similarity or the distance of the respective entry candidate to the reference utterances previously stored in the electronic dictionary, generally the vocabulary that already exists.

The entry is only saved in the electronic dictionary if the entry candidates are sufficiently far away or have a low enough similarity to the existing vocabulary. In the other case, an acoustic addition to the current entry is preferably requested. The experiment is repeated in the first stage after the acoustic addition.

In this respect, the invention is suitable for a scenario in which the speech recognition device is set up as an E bedded system, since in such a case the available computing power is relatively low and thus switching between different speech recognition units, for example a speech recognition unit for speaker-dependent speech recognition and a speech recognition unit speaker-independent speech recognition, is not feasible.

A control device for controlling a telecommunication device, for example one, is suitable as the control device for controlling a technical system

Telephone device, a fax machine, a PDA, a notebook etc., or to control a terminal in which at least two of the device functionalities described above are integrated in a common device. In particular, this device, which can be controlled with a clearly defined and limited vocabulary, can be controlled by means of a voice dialog, which voice dialog is relatively clear and thus can be implemented economically even by means of an embedded system.

Exemplary embodiments of the invention are shown in the figures and are explained in more detail below.

Show it

Figure 1 is a block diagram of a speech recognition device according to an embodiment of the invention;

FIG. 2 shows a block diagram in which the merging of an ^' electronic dictionary with words previously entered and trained exclusively for speaker-independent speech recognition and a dictionary in which utterances relating to speaker-dependent speech recognition are stored, which are merged according to the invention into a common dictionary for speaker-independent speech recognition ;

Figure 3 is a table in which the intended

Speech recognition states and the state transitions between different speech recognition states are shown;

Figure 4 is an illustration of a dialog state diagram according to an embodiment of the invention;

Figure 5 is a flow chart in which the individual

Process steps for speech recognition and for supplementing the electronic dictionary of Speech recognition device according to an embodiment of the invention are shown;

FIG. 6 shows a detailed illustration of the individual method steps for initializing the

Speech recognition device according to an embodiment of the invention;

FIG. 7 shows a message flow diagram in which the individual method steps for carrying out a

Voice dialogs are shown according to an embodiment of the invention;

Figure 8 is a message flow diagram in which the individual steps to complete an electronic

Dictionaries in the speech recognition device according to an embodiment of the invention are shown;

FIG. 9 shows a first functional diagram according to a ^"'

Embodiment of the invention;

Figure 10 shows a second functional diagram according to an embodiment of the invention;

FIGS. 11A and 11B are tables in which speech prompts presented to the user in the context of the speech dialogue according to a first exemplary embodiment of the invention (FIG. 9A) and additional actions of the speech recognition device (FIG. 9B) according to a first exemplary embodiment of the invention are shown;

FIG. 12 shows a speech dialog state diagram of a first state according to a first exemplary embodiment of the

Invention; FIGS. 13A and 13B show a speech dialog state diagram of a second state of a speech recognition device according to the first exemplary embodiment of the invention (FIG. 13A) and the associated flow diagram (FIG. 13B);

FIGS. 14A and 14B show a speech dialog state diagram of a third state of a speech recognition device according to the first exemplary embodiment of the invention (FIG. 14A) and the associated flow diagram

(Figure 14B);

FIGS. 15A and 15B show a speech dialog state diagram of a fourth state of a speech recognition device according to the first exemplary embodiment of the invention

(Figure 15A) and the associated sequence diagram (Figure 15B) -;

FIGS. 16A and 16B show a speech dialog state diagram of a fifth state of a speech recognition device according to the first exemplary embodiment of the invention (FIG. 16A) and the associated flow diagram (FIG. 16B);

FIGS. 17A and 17B show a speech dialog state diagram of a sixth state of a speech recognition device according to the first exemplary embodiment of the invention (FIG. 17A) and the associated flow diagram (FIG. 17B);

FIGS. 18A and 18B show a speech dialog state diagram of a seventh state of a speech recognition device according to the first exemplary embodiment of the invention (FIG. 18A) and the associated flow diagram (FIG. 18B); FIG. 19 shows a speech dialog state diagram of a first state of a speech recognition device according to a second exemplary embodiment of the invention;

Figure 20 is a speech dialog state diagram of a second

State of a speech recognition device according to the second embodiment of the invention;

FIG. 21 shows a speech dialog state diagram of a third state of a speech recognition device according to the second exemplary embodiment of the invention;

FIG. 22 shows a telecommunication device with a speech recognition device according to an embodiment of the invention;

Figure 23 shows a car radio with a speech recognition device according to an embodiment of the invention.

1 shows a speech recognition device 100 according to a

Embodiment of the invention.

Depending on the operating mode, the speech recognition device 100 operates in a first operating mode as a speech recognition device, in which

Speech recognition mode, the speech recognition device a spoken utterance 101, spoken by a user (not shown) of the speech recognition device 100, is recognized using a method for speaker-independent speech recognition. In a second

Operating mode, hereinafter also referred to as dictionary supplement mode, a spoken utterance is converted into a sequence of spoken units, subsequently into a sequence of phonemes, and, as will be explained in more detail below, possibly added to the electronic dictionary as a supplementary entry and therein saved. In both operating modes, the speech signal 101 spoken by the user is fed to a microphone 102 and, as the recorded electrical analog signal 103, is subjected to preprocessing, in particular preamplification by means of a preprocessing unit 104, in particular by means of a preamplifier, and as preprocessed and amplified analog signal 105 to an analog / digital converter 106 supplied, converted there into a digital signal 107 and supplied as a digital signal 107 to a computer 108.

In this context, it should be noted that the microphone 102, the preprocessing unit 104, in particular the amplification unit, and the analog / digital converter 106 can be implemented as separate units or else as units integrated in the computer 108.

According to this exemplary embodiment, it is provided that the digitized signal 107 is fed to the computer 108 via its input interface 109.

The computer 108 also has a microprocessor 110, a memory 111 and an output interface 112, all of which are coupled to one another by means of a computer bus 113.

The method steps described below, in particular the methods for supplementing the electronic dictionary and the respectively provided speech dialogue, are carried out by means of the microprocessor 110. An electronic dictionary 114, which contains the entries which contain speech words as reference words, is stored in the memory 111.

Furthermore, a digital signal processor (DSP) 123, which is also coupled to the computer bus 113, is provided, which is specific to the speaker-independent used Has speech recognition algorithms specialized microcontrollers.

A computer program, which is set up for speaker-independent speech recognition, is also stored in the digital signal processor 123. Alternatively, the algorithms used can be implemented in hard-wired logic, that is, directly in hardware.

Furthermore, the computer 108 is coupled by means of the input interface 109 to a keyboard 115 and a computer mouse 116 via electrical lines 117, 118 or a radio connection, for example an infrared connection or a Bluetooth connection.

Via additional cables or radio connections, for example an infrared connection or a Bluetooth connection 119, 120, the computer 108 is coupled to a loudspeaker 121 and an actuator 122 by means of the output interface 114.

Actuator 122 generally represents every possible actuator in the context of the control of a technical system in FIG. 1, for example implemented in the form of a hardware switch or in the form of a computer program in the event that, for example, a telecommunication device or another technical system, for example a car radio Stereo system, a video recorder, a television, the computer itself or any other technical system to be controlled.

According to the exemplary embodiment of the invention, the preprocessing unit 104 has a filter bank with a plurality of bandpasses, which measure the energy of the input speech signal 103 in individual frequency bands. So-called

Short-term spectra are formed by rectifying the output signals of the bandpasses, smoothing them and at short intervals are sampled, according to the exemplary embodiment, every 10 msec. The so-called cepstrum coefficients of two successive time windows as well as their temporal first derivation and their temporal second derivative are determined and combined to form a super feature vector and fed to the computer 108.

In the computer 108, as described above, a speech recognition unit for speech-independent speech recognition is implemented in the form of a computer program, the speech recognition based on the principle of the Hidden Markov models, according to the exemplary embodiment in the DSP 123.

In a basic vocabulary, which is stored in an electronic dictionary 114 at the beginning of the method, a hidden Markov model is stored for each basic entry, each in the following manner using a training data record, that is to say a set of training courses Voice signals, spoken by one or more training users, is determined.

According to this exemplary embodiment, the training of the Hidden Markov models takes place in three phases:

A first phase in which the speech signals contained in the training database are segmented,

• a second phase in which the LDA matrix (linear discriminant analysis matrix) is calculated and

A third phase, in which the code book, ie the HMM prototype feature vectors, is calculated for a number of feature vector components selected in a selection step.

The entirety of these three phases is referred to below as the training of the Hidden Markov models (HMM training).

The HMM training is carried out using the DSP 123 as well as using predetermined training scripts, vividly carried out by suitably equipped computer programs.

According to this exemplary embodiment, each phonetic unit formed, that is to say each phoneme, is divided into three successive phoneme segments, corresponding to an initial phase (first phoneme segment), a central phase (second phoneme segment) and an end phase (third phoneme segment) of a sound, that is to say of a phoneme.

In other words, each sound is modeled in a three-state sound model, that is, with a three-state HMM.

During speech recognition, the three phoneme segments are lined up in a Bakis topology or generally a left-right topology and the concatenation of these three lined up segments is carried out as part of the speaker-independent speech recognition.

As will be explained in more detail below, a Viterbi algorithm for decoding the feature vectors which are formed from the input speech signal 101 is carried out in the speech recognition mode.

After segmentation has taken place, the LDA matrix 304 (step 403) is determined by means of an LDA matrix calculation unit 303.

The LDA matrix is used to transform a respective super feature vector y to a feature vector x according to the following rule:

x = A ^{T •} (- y), ⁽ i ⁾

being with x a feature vector, A an LDA matrix, y a super feature vector,

• y a global displacement vector

referred to as.

The LDA matrix A is determined in such a way that

The components of the feature vector x are essentially uncorrelated from one another on a statistical average,

• the statistical variances within a segment class are normalized in the statistical average, • the centers of the segment classes are at a maximum distance from one another in the statistical average and

• The dimension of the feature vectors x is reduced as much as possible, preferably depending on the speech recognition application.

The method for determining the LDA matrix A according to these exemplary embodiments is explained below.

However, it should be noted that alternatively all known ones

Methods for determining an LDA matrix A can be used without restriction.

It is assumed that J segment classes exist, with each segment class j having a set of Dy-dimensional super

Contains feature vectors y, that is to say:

wobei mit Nj die Anzahl der in der Klasse j sich befindenden Super-Merkmalsvektoren yj bezeichnet wird.Class j = (2)

where Nj is the number of super feature vectors yj in class j.

With

J N = ∑Nj (3) j = l

is the total number of super feature vectors y.

Note that the super feature vectors yv are below

Using the segmentation of the speech signal database described above have been determined.

According to this exemplary embodiment, each super feature vector yv has a dimension Dy of

D _y = 78 (= 2 • 3 • 13)

, where 13 MFCC coefficients (cepstrums coefficients) are contained in the super feature vector yv, as well as their respective temporal first derivative and their respective temporal second derivative (this justifies factor 3 above).

In addition, each super feature vector y * contains the components of two time windows immediately following one another in the context of the short-term analysis (this justifies factor 2 above).

It should be noted in this connection that in principle any number of vector components adapted to the respective application can be contained in the super feature vector yv, for example up to 20 cepstrums. Coefficients and their associated temporal first derivatives and second derivatives.

The statistical mean or, in other words, the center of class j results from the following rule:

The covariance matrix ΣJ of class j results according to the following rule:

The average intra-scattering matrix S is defined as:

J ^S _w = ∑ (l) -∑j ' ⁽ 6 ⁾ j = l

With

p (τ) = -J-, (7)

N

where p (j) is called the weighting factor of class j.

In an analogous manner, the average inter-scattering matrix Sj _{b is} defined as:

J ib - Σ P IÖ) ^• fe [Ϊm - ϊϊ)) ^■■ ([ϊΫj, - ff (8) j = l With

as the average super feature vector across all classes.

The LDA matrix A is broken down according to the following rule:

A = U • W • V, (10)

being with

U a first transformation matrix,

• W is a second transformation matrix and • V is a third transformation matrix

referred to as.

The first transformation matrix U is used to diagonalize the average intra-scatter matrix S _w and is determined by transforming the positively definite and symmetrical average intra-scatter matrix S _w into its eigenvector space. In its eigenvector space, the average intra-scattering matrix S _{w is} a diagonal matrix, the components of which are positive and greater than or equal to zero. The components whose values are greater than zero correspond to the average variance in the respective dimension defined by the corresponding vector component.

The second transformation matrix W is used to normalize the average variances and is determined according to the following rule:

Die Transformation U-W wird auch als Weißung bezeichnet.

The transformation UW is also called whitening.

With

B = U • W (12)

the matrix B ^τ • S_ _w • B results in the unit matrix, which remains unchanged for any orthonormal linear transformation.

In order to diagonalize the average inter-scattering matrix S _f r, the third transformation matrix V is formed, which is formed according to the following rule:

where B • S_k ^■ B also represents a positively defined and symmetrical matrix that is transformed into its eigenvector space.

In the transformation space

x = A ^T • ^ - y) (14)

the following matrices result:

A diagonalized average intra-scattering matrix S _w :

S _w = diag (l) _d: = 1 ... D (15)

V

and a diagonalized average inter-scattering matrix S_b:

S3 _bh == ddiiaagg ((σσ ||)) _{d = 1} „, (16) where with diag (c _c j) j_ _{1 D} a Dy x Dy diagonal matrix with the

Components c ^ in the row / column d and otherwise with components with the value zero.

sind die Eigenwerte der Durchschnitts-Inter-The values

are the eigenvalues of the average inter

Scattering matrix Sj _b and represent a measure for the so-called pseudo-entropy of the feature vector components, which is also referred to below as the information content of the feature vector components. Note that the trace of each matrix is invariant with respect to any one

Orthogonal transformation, which results in the sum

Dy σ ² = ∑σ ^ (17). d = l

represents the total average variance of the average vector XJ of the J classes.

This results in a determined dependency of the pseudo-entropy of the feature vectors on the feature vector components contained or taken into account in the feature vector.

In accordance with this exemplary embodiment, a dimension reduction is then carried out by sorting the σ _^ values in order of decreasing size and omitting the σ ^ values, that is to say disregarding them that are smaller than a predetermined threshold value. The predetermined threshold value can also be defined cumulatively.

Then the LDA matrix A can be adjusted by sorting the rows according to the eigenvalues σ ^ the rows that are sufficient to be omitted Belong to "small" variances and thus have only a low information content (low pseudo-entropy).

According to this embodiment, the components with

2 uses the 24 largest eigenvalues σ _^ , in other words

D 'x 24.

The four sub-steps described above for determining the LDA matrix A 304 (step 403) are summarized in the following table:

The last method for the partial method in the course of training the Hidden Markov models is the clustering of the feature vectors, which is carried out by means of a cluster unit and which results as a result

Codebook has, in each case specifically for a training data record with a predetermined number of feature vector components.

The entirety of the representatives of the segment classes is referred to as a code book and the representatives themselves are also referred to as prototypes of the phoneme segment class.

The prototypes, hereinafter also referred to as prototype feature vectors, are determined in accordance with the Baum-Welch training described in [1].

The basic entries of the electronic dictionary, that is to say the basic entries for speaker-independent speech recognition, were created and stored in the manner described above and the corresponding hidden Markov models were trained.

There is therefore a Hidden Markov model for each basic entry.

The electronic dictionary with the basic entries 201 is designated by the reference symbol 200 in FIG.

As will be explained in more detail below, for one or more utterances that are spoken by a user and which in their entirety are clearly referred to as a speaker-dependent dictionary 202 in FIG. 2, each determined a sequence 203 of phonemes and saved as such a sequence 203 of phonemes as a new entry in the common electronic dictionary 204, which now contains the basic entries 201 and the new entries 203 in the form of phoneme chains.

The new electronic dictionary 204 thus clearly contains the basic entries 201 as well as the linguistic utterances converted into phoneme chains, that is to say the originally speaker-dependent entries, which can be regarded as speaker-independent representatives of new entries due to the conversion into phoneme chains.

In this way, speaker-independent speech recognition is made possible on the basis of the common electronic dictionary 204.

The common electronic dictionary 204 thus forms the search space for the Viterbi search in the context of speaker-independent speech recognition.

The expressions of a user are clearly mapped to a sequence of phonemes and a phoneme dictionary 202 is formed which contains the sequences of phonemes (phoneme chains).

Thus, no commands or words are recognized for the speaker-dependent part as part of speaker-independent speech recognition, but rather phoneme chains.

These phoneme strings are stored in the new electronic dictionary 204.

The addition of the user-defined entries to the electronic dictionary 200, that is to say the phoneme chains, is made possible in particular by file management in the, as will be explained in more detail below Computer 108, by means of which the storage of the speaker-dependent list entries and the basic entries in the speaker-independent dictionary 200 and the communication with the speech recognition application is implemented and managed.

According to this exemplary embodiment, the microprocessor 110 is the controller SDA 80D51U-A from Infineon Technologies AG and the method for forming hidden Markov models is based on the software and a digital signal processor (DSP) from Oak.

Electronic messages are used for communication between the microprocessor 110 and the DSP 123 from Oak in order to trigger predetermined events and actions in the microprocessor 110 or the DSP 123.

According to this exemplary embodiment of the invention, the following messages are provided for different speech recognition states, hereinafter also referred to as HMM states:

First, the speech recognition states permitted within the speech recognizer are explained.

As can be seen in FIG. 3, the speech recognizer has the following four HMM speech recognition states:

An initialization state INIT 301,

A stop state STOP 302,

A pause state PAUSE 303 and an operating mode state RUN 304.

As can be seen from the state transition diagram 300 in FIG. 3, the following state transitions are provided.

The initialization state INIT 301 can be changed to the stop state STOP 302, which happens automatically when all databases are loaded (step 305). Another transition from the initialization state INIT 301 to one of the other states PAUSE, RUN 303, 304 is not provided.

From the stop state STOP 302 can in the

Initialization state INIT 301 are passed if the loaded databases are inconsistent (step 306), in which case the InitHM SRDefault message is transmitted from the DSP 123 to the microprocessor 110.

If the "PAUSE" command in the form of the PauseHMMSR message is received by the microprocessor 110 from the speech recognizer, that is to say the DSP 123, the DSP 123 changes to the pause state PAUSE 303 (step 307).

After receiving the "RUN" command in the form of the StartHMMSR message from the microprocessor 110, the DSP 123 changes to the RUN 304 operating mode state (step 308).

The pause state PAUSE 303 can be changed to the initialization state INIT 301 (step 309) if the databases are inconsistent. This occurs in the case when the DSP 123 receives the InitHMMSRDefault message from the microprocessor 110.

After receiving the "STOP" command in the form of the StopHMMSR message from the microprocessor 110, the DSP 123 changes to the STOP state STOP 302 (step 310).

After receiving the "RUN" command in the form of the StartHMMSR message from the microprocessor 110, the DSP 123 changes from the pause state PAUSE 303 to the operating mode state 304 (step 311).

Finally, the speech recognition unit can go from the RUN 304 operating mode state to the initialization state INIT 301 return if the databases are inconsistent (step 312). This happens when the DSP 123 receives the InitHMMSRDefault message from the microprocessor 110.

After receiving the "STOP" command in the form of the StopHMMSR message from the microprocessor 110, the speech recognition unit, in other words the DSP 123, returns from the RUN 304 operating mode state to the STOP 302 stop state (step 313).

Finally, it is provided that the speech recognition unit changes from the operating mode state RUN 304 to the pause state PAUSE 303 after receiving the command "PAUSE" (step 314). This happens when the DSP 123 receives the message PauseHMMSR from the microprocessor 110 ,

In summary, the following messages are provided for communication between the microprocessor 110 and the Oak DSP 123:

In the initialization state INIT 301, in which the speech recognizer is initialized with default values after activation, the following messages are defined which can be sent to the Oak DSP 123 or from the Oak DSP 123:

InitHMMSRDef ult:

This message initiates the setting of default values for the speech recognizer in the Oak software in the DSP 123, • InitHMMSRPara s:

This message initiates the loading of the speech recognition parameters into the Oak DSP 123,

• StartLoadHMMLDA:

This message starts loading the program to determine the LDA matrix,

• StartLoadHMMDictionary:

With this message is loading an electronic Dictionary depending on the respective state or the respective speech dialog, started, CodebookBlockLoadedAndSwitched:

With this message, the Oak Software is informed in the DSP 123 that the Switched Memory Block (SMB), according to this embodiment of 16 KByte size, is accessible to the Oak Software, since the total number of blocks and segments contained in the Application to be taken into account by the speech recognizer in which microprocessor 110 is known.

In the STOP state STOP 302, in which the speech recognizer is deactivated, the following messages are provided, which can be sent to the Oak DSP 123 or from the Oak DSP 123:

InitHMMSRDefault,

InitHMMSRParams,.

StartLoadHMMLDA,

StartLoadHMMDictionary, • PauseHMMSR:

With this message the Oak DSP 123 is informed that the speech recognizer should go into the deactivated state, • StartHMMSR: With this message the speech recognizer in the Oak

DSP 123 started.

In the pause state PAUSE 303, in which the preprocessing is carried out in the speech recognizer, but no feature extraction has yet taken place, the following messages are provided, which can be transmitted to the Oak DSP 123 or from the Oak DSP 123:

InitHMMSRDefault,

InitHMMSRParams,

StartLoadHMMLDA,

StartLoadHMMDictionary,

StartHMMSR, StopHMMSR:

This message indicates to the Oak DSP 123 that the speech recognizer should be stopped and should go into the stop state 302, • CodebookBlockLoadedAndSwitched.

In the operating mode state RUN 304, in which the speech recognizer is fully active and carries out the speech recognition, the following messages are provided, which can be transmitted to the Oak DSP 123 or from the Oak DSP 123:

InitHMMSRDefault,

InitHMMSRParams,

StartLoadHMMLDA, • StartLoadHMMDictionary,

PauseHMMSR,

StopHMMSR,

CodebookBlockLoadedAndSwitched.

There is also an additional message

SetHMMSearchParams (minStableTime, wordStartupPenalty, transitionPenalty) are provided, with which the search parameters minStableTime, wordStartupPenalty and transitionPenalty can be set for the speaker-dependent dictionary.

The search parameter minStableTime specifies the time - in units of the number of frames - within which the hypothesis must not change in order to output the message HypothesisStable.

The search parameters wordStartupPenalty and transitionPenalty are used within the search to calculate the optimal path. The search parameter transitionPenalty specifies a penalty value that evaluates a transition from a state i to a state j. The search parameter wordStartupPenalty specifies an initial penalty value that is used to enter a new word model. This message can be transmitted to the microprocessor 110 by the speech recognizer in the Oak DSP 123 in any state of the firmware of the DSP 123. With the message SetHMMSearchParams (minStableTime, wordStartupPenalty, transitionPenalty) the search is reset and the parameters for the search space are defined.

The structure of the voice dialog states explained below is set out below in a voice dialog in which the voice recognition is carried out.

A speech dialog is used for the interactive communication of the speech recognizer with a human user in order to allow the user predefined control options and thus an interactive intervention in the system to be controlled, that is to say in the computer 108 using the speech recognizer.

In this context, it should be pointed out that the speech dialogue states should not be confused with the states of the speech recognizer itself described above.

Every speech dialog, i.e. every speech application, starts from a basic state after its activation.

According to this exemplary embodiment, a number of commands are defined for a speech application, which are also referred to below as keywords.

Each command can have a single word or multiple words. Each command is linked to an action that is uniquely assigned to the respective command (see voice dialog state diagram 400 in FIG. 4). Actions 408, each associated with a command 406 in the form of a command-action tuple (407, 409), can control a device, such as a CD player or a communication device, or another element of a stereo system or generally a technical system and terminate the speech recognition application, or perform additional actions in the same step, triggered with the same command, or, for example, emit a sound by means of the loudspeaker 121, and then change to the same speech dialog state or to a different speech dialog state.

In the speech dialog state diagram 400 in FIG. 4, a temporally preceding speech dialog state X1 401 is shown, as well as its transition to the current speech dialog state X 402, the speech dialog state diagram 400 also taking into account those to be taken into account in the current speech dialog state X 402 Words stored in an electronic dictionary 403, the electronic dictionary 403 containing both the words 404 previously stored in the form of speaker-independent, previously trained HMMs, generally the speaker-independent utterances with any number of words 404, and list entries 405 which originally contain speaker-dependent utterances which, however, as will be explained further below, are mapped to a sequence of phonemes, which are then accessible to speaker-independent speech recognition.

In a respective speech dialog state diagram 400, as explained above, the commands 406 and the actions 408 are each contained in a command-action tuple (407, 409).

According to this exemplary embodiment, the maximum length of a phoneme sequence with respect to its temporal length is or with regard to the number of permissible phonemes depending on the application.

According to this exemplary embodiment, 255 states are permissible per list entry 405, so that the largest number of permissible phonemes per list entry 405 is less than or equal to 85.

The commands are generated from the available vocabulary, that is to say from the words 404 or list entries 405 contained in the dictionary 403.

Each command 406, 407 is necessarily linked to an action 408, 409.

The command structure is as follows:

• command = one or more words,

• command = one or more words + a list entry,

• command = one list entry + one or more words, • command = one or more words + one list entry + one or more words,

• Command = a list entry.

In the context of this description, an action 407, 409 is a synonym for a reaction of the respective technical system that is fundamentally as complex as desired; in abstract terms, the reaction of the speech recognizer for controlling the actuator 122 in FIG.

Action 407, 409 provides, for example, feedback from the speech recognizer according to the invention and, in order to indicate to the user that something was recognized at all, switching to another speech dialog state, loading a new electronic dictionary, or executing an action assigned to the command , for example that

Dial an entered phone number. In this context it should be noted that the same action can be defined for different commands.

The communication between the microprocessor 110, that is to say the 80D51 controller and the digital signal processor 123 from Oak Technologies, is described below in the form of message flow diagrams.

As is shown in the flowchart 500 in FIG. 5, an acoustic signal is issued to the user by means of the loudspeaker 121 from a start state 501 after the DSP 123 has been activated, that is to say in other words after the speech recognizer has started, in order to signal the user, that the speech recognition process has been activated.

Starting from the start state 601, a transition is made to a first cycle (Cycle_0) 502, in which the HMMs are initialized.

Subsequently, a transition is made to a second cycle (Cycle_l) 503 and after its execution it is checked whether the speech recognition process is to be ended (test step 504) and, in the event that the speech recognition process is to be ended, one

End state 505 passed, in which the speech recognizer is deactivated.

However, if the speech recognition is not to be ended, an additional test step (test step 506) is used to check whether a change should be made to a new speech dialog state.

If this is the case, then the second cycle 503 is carried out for the new speech dialog state. However, if the speech dialog state is not to be changed, a third check step (check step 507) checks whether a change should be made in the electronic dictionary, for example whether a new entry should be added to the electronic dictionary or whether an entry from the electronic dictionary is to be removed or whether only an entry in the electronic dictionary is to be changed.

If this is the case, the system branches again to the second cycle 503.

If this is not the case, however, a third cycle (Cycle_2) 508, which will be explained in more detail below, is carried out.

After the third cycle 508 has ended, a fourth test step (test step 509) again checks whether the speech recognition is to be ended.

If the speech recognition is to be ended, a transition is made to the end state 505 and the speech recognizer is deactivated, otherwise a branch is made to the second test step 506, in which it is checked whether a new speech dialog state is to be assumed.

6 shows the implementation of the first cycle 502 in detail in a message flow diagram 600.

In the first cycle 502, the HMMs are initialized.

In an initialization phase, in which the speech recognizer is in the initialization state INIT 301, a message StartHMMSRFlowgraph 601 is transmitted from the microprocessor 110 to the DSP 123, with which the respective HMM in the DSP 123 is started. In response to the StartHMMSRFlowgraph 601 message, the DSP 123 sends a confirmation message 602 to the microprocessor 110.

A message InitHMMSRParams 603 is then sent by the microprocessor 110 to the DSP 123, which activates the loading of the speech recognition parameters into the DSP 123.

In response to the InitHMMSRParams 603 message, a confirmation message 604 is transmitted from the DSP 123 to the microprocessor 110.

In a further step, a StartLoadHMMLDA 605 message is sent from the microprocessor 110 to the DSP 123 in order to start the loading of the computer program which causes the determination of an LDA matrix, as described above, for the respective HMM.

In response, the DSP 123 sends a message SMBRequestLoadHMMLDA 606 to the microprocessor 110, which responds to this message with a confirmation message 607, with which the microprocessor 110 indicates that the program codes necessary for performing a linear discriminant analysis are available in a switched memory block.

In a further message StartLoadHMMDictionary 608, which is sent from the microprocessor 110 to the DSP 123, the microprocessor 110 transmits to the DSP 123 the electronic dictionary for the basic dialog state of the respective speech dialog in the respective application in the DSP 123.

The DSP 123 responds to the receipt of the StartLoadHMMDictionary 608 message with a message

SMBRequestLoadHMMDictionary 609, with which the active vocabulary of the respective electronic dictionary from the Microprocessor 110 is requested. This request SMBRequestLoadHMMDictionary 609 is acknowledged with a confirmation message 610 from the microprocessor 110 after it has been received.

Subsequently, a message SMBRequestCodebookBlock 611 is transmitted from the DSP 123 to the microprocessor 110 and the microprocessor 110 responds with a message CodebookBlockLoadedAndSwitched 612 with which the microprocessor 110 transmits the switched memory blocks (SMBs) with the requested codebook data to the DSP 123.

In a further message SMBRequestCodebookBlock 613, the DSP requests additional blocks in which the required code book, in other words the required code book data, is contained.

The microprocessor 110 in turn reacts to the message SMBRequestCodebookBlock 613 with a message CodebookBlockLoadedAndSwitched 614, with which it transmits one or more further SMBs with the required code book data to the DSP 123, the total number of blocks and required segments now being known in the speech recognizer ,

The speech recognizer then goes into the STOP state STOP 302 and only leaves this state after receiving the "Start" command, which the microprocessor 110 transmits to the DSP 123 by means of the StartHMMSR 615 message, and the DSP 123 confirms receipt of the StartHMMSR message 615 with a confirmation message 616.

In the operating mode state 404, the DSP 123 sends a message SMBRequestCodebookBlock 617 to the

Microprocessor 110 transmits, which then periodically sends a response message, also for each frame a message CodebookBlockLoadedAndSwitched 618 transmitted to the DSP 123, with which the SMB was switched and a new codebook block was transmitted by the microprocessor 110 to the DSP 123.

The messages SMBRequestCodebookBlock 617 and CodebookBlockLoadedAndSwitched 618 are exchanged for each frame between the microprocessor 110 and the DSP 123 until the DSP 123 transmits the speech recognition result in a message HMMHypothesisStable 619 to the microprocessor 110, which receives an acknowledgment message 620 upon receipt responding.

Despite transmitting the speech recognition result, the DSP 123 remains in the RUN 304 operating mode state.

Only after receiving a PauseHMMSR 621 message, which is sent by the microprocessor 110, does the DSP 123 go into the PAUSE 303 pause state and, however, does send one before

Confirmation message 622 to microprocessor 110.

A speech recognition result is thus available in the microprocessor 110 and the microprocessor 110 now decides what should happen next in the speech dialog, depending on the application.

In the following it is assumed that an application controls several different devices, whereby a telecommunication device, in particular a telephone, is only one of many.

In this case, in a first dialogue step of the speech dialogue, a method for speaker-independent speech recognition is used to determine which device is actually to be controlled, for example whether a CD player, a tape recorder, a cassette recorder, a radio, a telecommunication terminal (such as a telephone, a facsimile device, a teletext device, a mobile radio device, a PDA, etc.) is to be controlled.

Without restricting the general applicability, it is now assumed that a telephone is selected as the device to be controlled in the first voice dialog step, so that the result of the first cycle 502 is that the menu should be changed, in other words the voice dialog state to control a phone.

In the case when a state transition from one speech dialog state to another speech dialogue state is to take place, there is usually a change in the electronic currently used in the context of speech recognition

Dictionary, which is usually dependent on the respective speech dialog state, required.

In this case, the second cycle 503 is performed, with the exchanged messages between the microprocessor

110 and the DSP 123 is shown in detail in a message flow diagram 700 in FIG.

In a first phase, in which the speech recognizer is in the pause state PAUSE 303, a message SetHMMSearchParams 701 is transmitted by the microprocessor 110 to the DSP 123 in order to indicate to the DSP 123 that it should load new parameters for the search. The receipt of this message is confirmed with a confirmation message 702 from the DSP 123 to the microprocessor 110.

A message StartLoadHMMDictionary 703 is then transmitted from the microprocessor 110 to the DSP 123, by means of which message the loading of the electronic dictionary for the respective new speech dialog state into the DSP 123 is started. With a message SMBRequestLoadHMMDictionary 704, the signal processor 123 requests the respective electronic dictionary from the microprocessor 110, divided into blocks (SMB) of 16 KB each. With a confirmation message 806, the microprocessor 110 indicates that the requested electronic dictionary is available in SMBs and can be copied from the DSP 123 to another location.

By means of a message StartHMMSR 706, which from the

Microprocessor 110 is sent to and received by the DSP 123 and is confirmed by the DSP 123 by means of a confirmation message 707, the speech recognizer in the DSP 123 changes to the RUN 304 operating mode state and a message exchange takes place in a second phase, in which the DSP 123 transmits an SMBRequestCodebookBlock 708 message to the microprocessor 110 for each frame, which responds to this message with a CodebookBlockLoadedAndSwitched 709 message, likewise for each frame. With the message

CodebookBlockLoadedAndSwitched 709 is informed to the DSP 123 by the microprocessor 110 that the SMB has been switched and that a new codebook block with codebook data has been loaded on the part of the microprocessor 110 and is therefore available for the DSP 123.

These messages SMBRequestCodebookBlock 708 and CodebookBlockLoadedAndSwitched 709 are exchanged for each frame, as described above, until the speech recognizer has determined a speech recognition result, whereupon the DSP 123 transmits a message HMMHypothesisStable 710 to the microprocessor 110, which simultaneously indicates that and which speech recognition result has been determined by the DSP 123.

Again, the speech recognizer remains in the RUN 304 operating mode state. The microprocessor 110 responds to the HMMHypothesisStable 710 message with a confirmation message 711 and only after receiving a "pause" command does the microprocessor 110 transmit a PauseHMMSR 712 message to the DSP 123, which responds to the receipt of this message with a confirmation message 713, whereupon the speech recognizer enters the message PAUSE 303 paused.

In summary, regarding the second cycle 503 shown in FIG. 7, it should be noted that in the event that the speech recognizer is in a speech dialog state in which both basic entries (speaker-independent) and list entries (per se speaker-dependent, converted into phoneme sequences) are used are also independent of the speaker) are contained in a dictionary, each new dictionary is a dynamic dictionary.

As described above, it contains speaker-independent commands and speaker-dependent, user-defined commands

List entries, for example in a phone book list.

The list entries according to this exemplary embodiment of the invention are stored in a fixed memory location of the flash memory, which is provided as memory 111 in the computer 108.

According to the invention, new list entries can be added to the electronic dictionary and old, no longer required list entries can be removed from the electronic dictionary, so that a dynamic, that is to say a changeable, number of words is contained in the electronic dictionary which can be recognized by the speech recognition unit using a speaker-independent speech recognition technique. It should also be noted that the search space also depends on the current number and size of the basic entries contained in the dictionary and list entries is dependent. For this reason, the most efficient file management, in particular efficient management of the electronic dictionaries, makes sense.

To add or remove list entries from the speaker-dependent part of the respective dictionary, that is, the list entries in the dictionary, a change in the current dictionary is required.

The third cycle 507 is provided in particular for adding new list entries, as is shown in detail below in a message flow diagram 800 (cf. FIG. 8).

The third cycle 507 is executed when a state transition from one speech dialog state to another speech dialog state does not require a change in the dictionary.

An example of such a state transition is an intrinsic loop, that is, a transition from a speech dialog state to itself.

As can be seen in FIG. 8, in a first phase a message StartHMMSR 801 is transmitted from microprocessor 110 to DSP 123, which then acknowledges receipt of the message StartHMMSR 801 with a confirmation message 802, which puts the speech recognizer in the operating mode state RUN 304 is located.

Subsequently, the DSP 123 transmits a message SMBRequestCodebookBlock 803 in a corresponding manner, as described above in connection with the second cycle 603, to the microprocessor 110, which in turn, as described above, for each frame with a message CodebookBlockLoadedAndSwitched 804 reacts and thus provides the requested data to the DSP 123.

The exchange of the messages SMBRequestCodebookBlock 803 and CodebookBlockLoadedAndSwitched 804 takes place in a corresponding manner until a result of the speech recognition has been determined by the DSP 123 and the result is transmitted by means of a message HMMHypothesisStable 805 to the microprocessor 110, which receives the message HMMHypothesisStable 805 acknowledged with a confirmation message 806.

Again, the speech recognizer remains in the RUN 404 operating mode state and only after receiving a "pause" command does the microprocessor 110 send a PauseHMMSR 807 message to the DSP 123, which acknowledges receipt with an acknowledgment message 808, whereupon the speech recognizer goes into the pause state PAUSE 403 passes.

In summary, the respective HMM is thus initialized in the first cycle 502, which is always carried out after an HMM speech dialog is started.

A new electronic dictionary is usually provided in the DSP for each new speech dialog state

123 to load. To achieve this, the second cycle 503 is performed. In the event that the current dictionary is changed and does not change to another dialog state, the second cycle 503 is also used.

If the current speech dialog state remains without changing the dictionary, the third cycle 507 is carried out. Thus, two operating levels to be distinguished from one another are usually provided in a speech recognition application according to the invention.

The first operating level is formed by the communication between the DSP 123 and the microprocessor 110 and the speech recognition carried out by the DSP 123 of a speech signal spoken by a user.

The second level of operation is the level of software that runs on the microprocessor 110, in other words, the speech dialog.

Thus, the tasks in a speech recognition application are divided between the microprocessor 110 and the DSP 123 in such a way that the less computationally intensive implementation of the speech dialog is usually carried out by the microprocessor 110, and the very computation-intensive actual speech recognition by the DSP 123.

The file management, in particular the management of the electronic dictionaries, is carried out by the microprocessor 110.

The microprocessor 110 performs the following tasks in particular:

Adding a new list entry to the respective dictionary,

Removing a list entry from the respective dictionary,

• Remove the entire list from the dictionary.

The three tasks described above are explained in more detail below:

1. Remove the entire list from the relevant electronic dictionary The voice dialog starts with the first cycle 502. Each state transition from one voice dialog state to the next causes the second cycle 503 to be executed.

After recognizing the command "delete list" the file management is started.

All list entries in the list of the electronic dictionary are deleted.

Subsequently, an electronic dictionary still exists, which, however, now only contains the speaker-independent basic entries or is even empty if the dictionary only contained speaker-dependent and user-defined entries.

After the list is deleted from the dictionary, the speech recognition process is either ended (step 505) or continued in the third cycle 507 or the second cycle 503.

2. Remove a single list entry from the respective dictionary

Again, the speech dialog is started in the first cycle 502, and possibly one or more state transitions have previously been performed using the second cycle 503 to other speech dialog states.

If the command "delete [entry]" is recognized, the file management is started by the microprocessor 110. The phoneme chain [entry] represents the recognized speaker-dependent list entry in the dictionary.

This entry is removed from the list in the respective dictionary. Furthermore, according to this exemplary embodiment it is provided that the memory management reorganizes the memory which is occupied by the list entry and thus releases it again to be occupied by other list entries. In this way, economical memory management can be implemented.

In order to ensure that the correct desired list entry is actually removed from the electronic dictionary, a security loop can be provided according to the invention, in which the user is asked again whether he really wants to delete the entered list entry. This possibly means a self-loop in the current speech dialog state without changing the dictionary, that is to say in this case the third cycle 507 is carried out.

In this case, the phoneme chain [entry] and the “delete” command are buffered. After the desired entry has been removed from the dictionary or after the delete command based on a user input with which it is indicated in the security loop that the specified entry is not deleted is to be ended, the speech dialog and thus also the speech recognition process can be ended (step 505) or that

Speech recognition method can be continued by means of a transition to another dialog state (second cycle 503) or a self-loop in the current dialog state (third cycle 507).

3. Add new list entries to the respective dictionary

This task is the most complex routine. As in the previous two procedures, the first cycle 502 is started this time and the second cycle 503 may have been performed one or more times. After receiving the command "Add [entry]", which was recognized by the speech recognizer, the system goes into a speech dialog state, in which the phoneme dictionary is loaded, in which phoneme dictionary the available phonemes, each one depend on the language used, are included.

The speech recognizer asks the user to speak the respective utterance which is to be added to the dictionary as a list entry one or more times into the speech recognition system.

It can be seen that the utterance must be spoken into the speech recognition system at least once. As will be explained in more detail below, the recognition rate for the list entry is the better, the more representational utterances of the same speech utterance are obtained from the speech recognition unit, in other words, the more often the same speech utterance by the user in the

Speech recognition system is spoken.

Furthermore, it is assumed that three representational utterances are available, that is to say that the speech utterance has been spoken three times by the user into the speech recognition system.

According to the invention, a computer variable is provided which determines the number of inputs of a speech utterance into the speech recognition system, in other words, the number of

Representative utterances indicate which variable is incremented for each new representative utterance. After the first utterance has been spoken, the third cycle 507 is carried out, the first utterance is temporarily stored in a buffer as a representative utterance, and the value of the computer variable described above is increased by the value “1”. In the case in which the value of the computer variable is "3", the procedure explained in more detail below is started, in which it is checked whether the utterance is stored as a new list entry in the electronic dictionary or whether the desired utterance is shown in cannot be saved in the electronic dictionary.

In accordance with this exemplary embodiment of the invention, it is clearly checked for an utterance to be entered as a list entry whether several spoken-in speech signals for the same utterance are sufficiently similar in a comparison space and at least one of the representational utterances of the spoken-in speech signals for a same utterance is a sufficiently large distance of the words or list entries already stored in the dictionary and only if these two conditions are met, the electronic dictionary is supplemented by the new spoken utterance.

In this way it is possible to implement an electronic dictionary for speaker-independent speech recognition in a user-friendly and resource-saving manner, the following framework conditions being sought:

• The smallest possible number of entry assumptions should take place in the event of unequal acoustic expressions;

• The highest possible number of entry assumptions should be made with the same acoustic utterances;

• The number of additional acoustic additions should be as small as possible, which would lead to resource problems;

• A vocabulary should be formed which offers the highest possible recognition rate.

Clearly, similarity measures or distance measures are used as threshold value parameters, which means that, using statistical methods, the optimal range of the speech recognizer for a predetermined number of in the Dictionary contained words or list entries can be determined.

To solve the optimization problem mentioned above, two parameters are introduced below:

• MIN_FOR_WORD: This parameter, also referred to below as the intra-similarity value, is used to determine the similarity between the entry candidates,

• MAX_TO_DICT: This parameter, hereinafter also as

The inter-threshold is used to determine the similarity between an entry candidate and an entry of the existing vocabulary.

Based on the assumption that the variables MIN_FOR_WORD and MAX_TO_DICT are statistically independent of one another, the optimal threshold values for the respective application are determined independently of one another, the threshold values being determined in a training phase. The threshold values determined in the training phase are accordingly used as constant values in operation.

The training procedure for determining the threshold values is explained below for the specific case of two entry candidates. However, it should be pointed out that the method can be applied to any number of entry candidates for a speech utterance.

In addition, the number of speaker-dependent entries is set to N.

The distance d (s_, s _j ) is used as a measure of similarity. The distance d (sj_, sj) is a measure of the distance between the phoneme sequences s ^ and SJ. According to this In the exemplary embodiment, a standardized distance is used, since the phoneme chains can also have unequal lengths.

In principle, any measure that is suitable for determining a distance between two symbol chains, that is to say clearly between two sequences of spoken units, according to this exemplary embodiment, between two phoneme sequences, for example the so-called Levenstein distance measure or the so-called Mahalanobis distance, can be used as a distance measure , are used.

Any comparison standard that meets the above requirement can also be used.

First, both the acceptance rate (AR) and the false acceptance rate (FAR) are determined to determine the intra-threshold value.

In this case, a threshold value variable T takes numbers from the range of values of the intra-threshold value MIN_FOR_WORD. For each realization of the threshold value variable T, the function values AR (T) and FAR (T) are determined using a loop that includes all N entries.

The function curve is then plotted for both functions using the threshold value variable T. The optimal intra-threshold value MIN_FOR_WORD * is determined by evaluating an optimality criterion which is explained in more detail below.

First, the acceptance rate AR for the same acoustic

Expressions of speech, that is to say in the event that s = SJ, are calculated.

In this case, on a statistical average, the relative distances d (s, sj) between the entry candidates should only assume small values, ie the distance should go against the value "0". For a small one Threshold value variable value T, however, the values of the distance d (si, Sj) can exceed the threshold value variable value T, so that the acceptance rate would be low. For a large threshold variable value T, however, the acceptance rate increases relatively quickly.

The acceptance rate results according to the following regulation:

_A R ( _T ) = ^ AR (T)

N

where N ^ R (T) is the number of acceptances for a threshold variable value T.

The following rule is used as an acceptance condition that an entry candidate is accepted if:

d (si, sj) <T. (19)

The function AR (T) will also assume a small value for a small threshold value variable T, then a monotonically increasing function curve results until the saturation of the function AR (T), that is to say AR (T = 1), is reached.

The false acceptance rate (FAR) for unequal acoustic utterances, that is to say in the event that s _± «SJ, is then calculated.

In this case, the values of the relative distance d (si, S _j ) between the

Entry candidates accept larger values. For a small threshold variable value T, the distance d (si, sj) would often exceed the intra-threshold value and the false acceptance rate is therefore low. For a larger threshold variable value T, the false acceptance rate increases relatively slowly. The false acceptance rate is determined in this exemplary embodiment of the invention in accordance with the following regulation:

FAR (T) = ^{AR (T)} , (20)

N

where NFAR (T) denotes the number of false acceptances for a threshold variable value T.

The false acceptance condition according to this exemplary embodiment is:

The FAR (T) function is also used for a small one

Threshold variable value T assume a small value and there is also a monotonically increasing function curve in this case.

In comparison to the FAR (T) function, however, the saturation will only occur for a larger threshold value value T compared to the AR (T) function. Thus, the functional image of both functions AR (T) and FAR (T) corresponds roughly to that of a hysteresis curve.

If you wear both functions against the

Threshold value variable T as a parameter, the optimal intra-threshold value MIN_FOR_WORD * is obtained at the point at which the two curves of the functions AR (T) and FAR (T) have the greatest distance from one another, as is the case in the function diagram

900 is sketched in Fig. 9, that means:

MIN _ FOR _ WORD * = arg max | JAR (τ) - FAR (τ) |]. (22)

T

The optimal inter-threshold value is then calculated.

With this calculation it should be noted that after each Rejection of an utterance to be entered after a comparison has been made with the content of the electronic dictionary, an acoustic addition, that is to say that the user should request the same utterance again.

An acoustic addition is to be understood as speaking an additional parameter to the utterance to be spoken in, for example in the event that the utterance is a surname of a person, in addition the first name of that person.

However, an acoustic addition is not absolutely necessary according to the invention; alternatively, the application for entry of the new utterance in the electronic dictionary can also be rejected or the rejection can be made after a predetermined number of spoken utterances, according to which there is still no sufficiently high-quality signal, be rejected.

For the following explanation it is assumed that only one comparison per entry is permitted. In other words, the acoustic expansion according to the exemplary embodiment described below is not provided.

If one finds an optimal threshold value for this case, the number of acoustic additions is reduced to a reasonable level.

In this case, the threshold value variable T takes numbers from the range of values of the inter-threshold value MAX_TO_DICT.

Using the independence assumption as set out above can be used to carry out the second

Optimization task, the previously determined intra-threshold value MIN_FOR_WORD * can be used. First, the acceptance rate (ERA) is measured on the inter-threshold value MIN_FOR_WORD *.

The relative number of speaker-dependent entries EAR (T) is measured for each threshold value variable value T from the value range of the inter-threshold value MAX_TO_DICT, that is, EAR (T) results according to the following rule:

EAR (τ) = ^N EARW ₍₂₃ )

N

where NEAR (T) denotes the number of accepted candidates for a threshold variable value T.

The following rule is used as an acceptance condition:

d (w _{k +} ι, W)> T, (24)

being with

• W is the vocabulary already saved in the dictionary, that is the saved words or the saved list entries (W = [wi, W ₂ , W ₃ , ..., wj) and • wjς ₊ ι the new entry

referred to as.

For a small threshold variable value T, entries are also accepted which are only a short distance from the existing vocabulary W in the respective comparison space. On the other hand, hardly any entries are made for a large threshold value variable T. The function EAR (T) thus has a monotonically falling course. The recognition rate for the current threshold value variable T is then determined using the current total vocabulary M (T).

In this context it should be noted that the total number of entries in the dictionary depends on the current threshold variable value T. If there are speaker-dependent and speaker-independent entries in the respective common dictionary, the total word estimate M (T) results from the sum of the number of speaker-dependent entries and the speaker-independent entries. The detection rate ER (T) thus results from the following rule:

_{ER (τ) =} CRWÖ N

where CR _W (T) denotes the number of correctly recognized words for a threshold variable value T.

For a small threshold variable value T, a relatively large number of entries are recorded in the common electronic dictionary, the risk of confusion is accordingly high, but the word recognition rate is relatively low. For a large threshold variable value T, fewer entries are accepted for storage in the common dictionary, but as a result of the increasing distance between the entries in the vocabulary, the recognition rate ER (T) increases. The function ER (T) thus has a monotonically increasing profile.

To determine the optimality criterion, it should be noted that the requirement applies to find an optimal range of the inter-threshold value MAX_TO_DICT for a fixed N.

A compromise between the number of entries to be recorded and the associated recognition rate ER (T) is therefore necessary. If the function EAR (T) is observed until after leaving the maximum, that is, as long as EAR (T) has the value “1”, in which area N words are always recorded for storage in the electronic dictionary, the corresponding recognition rate ER ( T) can be determined as a function of the threshold value variable T by means of simple reading or by means of an appropriate automated evaluation.

It should be noted that the detection rate is normalized until the maximum is exceeded from EAR (T) to the value M (T) = N.

This results in a working range for the inter-threshold value MAX_TO_DICT, which is limited to low values of the threshold value variable value T by the minimum recognition rate ^ER MIN | N with a fixed predetermined number of speaker-dependent entries N in the dictionary.

This situation is shown in the function diagram 1000 in FIG. 10. The inter-threshold MAX_TO_DICT is limited upwards by the maximum recognition rate ERM ^ XIN given a fixed number of speaker-dependent entries in the dictionary.

The following therefore apply to the inter-threshold value MAX_TO_DICT uss:

This two-stage statistical method according to the invention has the advantage that, given the number of speaker-dependent entries N, a work area is found in which the recognition rate can move.

Conversely, it is also possible to request a minimum recognition rate and then the maximum number of entries that are permitted to be stored in the dictionary.

In the speech dialog state, in which speaker-dependent and speaker-independent entries are stored in the dictionary, it is possible to add new user-defined names, that is to say generally user-definable utterances in the dictionary, as a list entry or to delete an old list entry from the dictionary.

In both cases, the microprocessor 110 manages the file that represents the dictionary. After the file has been changed, the speech recognition unit can be activated again for speech recognition.

As long as the speech dialogue continues, the second cycle 503 is repeated, in which cycle the message StartLoadHMMDictionary is provided with the respective identifier, that is to say the ID of the respective defined dictionary, it should be noted that the ID remains unchanged for the respective application and cannot be changed at runtime.

In order to insert a new entry into the electronic dictionary, this means that the electronic dictionary is not changed for the first step, which is why the third cycle 507 is carried out in order to return to the current speech dialog state.

To make a new statement on the speaker dependent list in the

To add a dictionary, a special dictionary is loaded, namely the phoneme dictionary. The utterance is analyzed using the phonemes stored in the phoneme dictionary. The file management of the dictionary file, which has saved speaker-dependent list entries, is a task of the microprocessor 110, as stated above.

After recognizing a command which triggers the application to delete an entry in the dictionary or to add an entry to the dictionary, the speech recognizer can be put into the pause state PAUSE 303 or it can be ended (step 505).

Then the file management can be done.

The file management process in which the dictionary is accessed starts by comparing the speaker-dependent spoken utterance with all entries stored in the dictionary, both with the speaker-dependent entries and with the speaker-independent entries.

In the event that an entry is to be deleted from the dictionary, the corresponding entry is searched in the entire dictionary.

The file manager is responsible for deleting the entries or changing any entries only in the speaker-dependent list of entries in the dictionary.

In the context of file management, the microprocessor 110 knows the memory size available for the dictionary, that is to say in particular the microprocessor 110 knows at which point in the memory 111 the speaker-dependent list begins and at which it ends.

In the case where the memory 111 is full, or in other words, in the case where not enough

Space to record a new utterance in the Memory 111 is included, the request to register a new statement is rejected.

The rejection can be done using special voice prompts, for example predefined and recorded voice prompts for the different cases:

A possible language prompt to be output to the user in the event that an input which was actually intended as a command was not recognized as a word which is contained in the dictionary is: "What?"

• In the event that the utterance that is to be added to the dictionary already exists in the dictionary, a possible language prompt to be output to the user is:

"[Entry] is already available."

• In the event that there is no more storage space available, a possible voice prompt to be output to the user is: "[List] is full."

The following is an example of such administration in a metalanguage in a C pseudo code:

StartDiatσguö (H

State_1 (Actlon) {// Dialogue atate 1, basic State cycleJJ (HMMHyρothtssisStab! E (RβcResult)) = true) thβπ {case (

RecResult »CD-Player: Actlαn« goto state ä; da b, a RecResu! t = * Täpe: Actlon »goto statβ._3j do c, a ReeResuttβ Radio: Acft» «state_4; do d, a RecResult ~ Telephone: AcliOπ - goto state Sϊ da e, a RecResuit »eancel: Action« StopHM SRFIawgraph; do f

)

}

}

} do (action)

do l, m, t da ιt, a stαf

do f

(do u, s

} dα <AcUαn) A first exemplary embodiment for a concrete speech dialogue is explained in more detail below.

Different speech dialog states are specified and the actions of the system are shown, which are carried out after recognizing a defined command.

The voice dialogue according to this exemplary embodiment of the invention is a simplified schematic telephone voice dialogue.

In FIGS. 11A and 11B, the speech prompts (FIG. 11A) defined according to this exemplary embodiment are listed in a first table 1100 and additional system reactions in table 1101 shown in FIG. 12B.

A voice prompt is to be understood as a predefined utterance of the system, which either represents a voice utterance of a system administrator that has previously been recorded and is simply reproduced by the computer 108, or it can be a synthesized voice signal that is generated from textual information about a voice signal by the computer 108 was converted.

Actions of the are under the additional system reaction

Systems to understand after a special command has been recognized by the speech recognizer.

12 shows an HMM state diagram 1200 for a first state 0 in which the HMMs have not yet started.

The state diagram 1200 is to be understood in such a way that after receipt of the command 1201 StartHMMSRFlowgraph 1202, the action 1203 of the state transition 1204 into the second state and the output 1205 of the voice prompt <a>, that is to say the output of the beep by means of the loudspeaker 121. FIG. 13A shows an HMM state diagram 1300 for the second state 1 and FIG. 13B shows the associated flow diagram.

As can be seen from the speech dialog state diagram 1300, the dictionary in this second HMM state 1 has the following entries: "CD player, cassette recorder, radio, telephone, cancel", in other words, the speech recognizer loads in the second speech dialogue state 1 this dictionary and can only recognize the words contained in this electronic dictionary.

If the speech recognizer recognizes the received words as a command as they are contained in the command list in the speech dialog state diagram 1300, a corresponding state transition is initiated in a next subsequent state, the speech dialogue states 2, 3 and 4 being further explained for reasons of Clarity can not be explained in more detail.

Thus, without restricting the generality, only the voice dialog with regard to the telephone application is explained in more detail below, that is to say the branching of the voice dialog for the case when the "telephone" command has been recognized and thus into the sixth voice dialog state 5 as it is in the speech dialog state diagram 1400 in

Fig. 14A and the associated flow diagram 1410 is shown in Fig. 14B.

The dictionary of the sixth speech dialog state 5 has the following terms: "Number, Dial, Name, Save, Delete, Cancel" as basic entries, that is to say as speaker-independent entries and a list of speaker-dependent entries, designated in FIG. 14A with <name> ,

In the event that the "dial number" command has been entered by a user and recognized by the speech recognizer, is branched into a seventh speech dialog state 6 and the speech prompts <g> and <a> are output.

The speech dialogue state diagram 1500 for the seventh speech dialogue state 6 is shown in FIG. 15A and the associated flow diagram 1510 in FIG. 15B.

The dictionary in the seventh speech dialog state 6 has the following entries: "zero, one, two, three, four, five, six, seven, eight, nine, dial, cancel", which words in the seventh speech dialog state 6 of the speaker-independent speech recognizer can be recognized.

Depending on which command is recognized by the speech recognizer, either the seventh speech dialog state 6 remains, for example in the case when digits are recognized, which are temporarily stored or the first state 0 is entered in the event that the "Select" command or "Cancel" command is detected.

In the event that the "memory name" command was recognized in the sixth speech dialog state 5, the system branches to the eighth speech dialog state 7, which is shown in the speech dialog state diagram 1600 in FIG. 1A and the associated sequence diagram 1610 in FIG. 16 is shown.

For the eighth speech dialog state 7, an electronic dictionary is provided with the following entries: "zero, one, two, three, four, five, six, seven, eight, nine, dial, cancel".

It is further provided that in this state essentially three commands can be recognized and processed, namely the input of individual digits, whereupon the eighth speech dialog state 7 remains and the respectively recognized digit is temporarily stored; the command to save, whereupon in a further explained the ninth voice dialog state 8 is changed to output the voice prompt <p> and the beep <a> and the command "Cancel", whereupon the first voice dialog state 0 is passed to output the voice prompt <f> (cf. Fig.llA).

The voice dialog state diagram 1700 of the ninth voice dialog state 8 is shown in Fig. 17A and the associated flow diagram 1710 is shown in Fig. 17B.

In the ninth speech dialog state 8, an input name is converted into a sequence of phonemes using the phoneme dictionary, which is the dictionary of the ninth speech dialogue state.

After recognizing the command <name>, the tenth speech dialog state 9 is entered, in which the respective list entry is stored in the electronic dictionary.

The speech dialog state diagram 1800 for the tenth speech dialogue state 9 and the associated flow diagram 1810 are shown in FIGS. 1A and 1B.

After the name has been saved in the electronic dictionary, the transition to the first speech dialog state 0 takes place.

A second, simplified exemplary embodiment of the invention is explained in more detail below.

19 shows a speech dialog state diagram 1900 of a first speech dialog state 1 according to the second exemplary embodiment of the invention. The dictionary of the first speech dialog state 1 has the following entries: "Name, Save, Delete, Dial, Phonebook, Help, Yes, No, List of Names".

The following commands 1902 are defined in the first speech dialog state 1 and can be recognized by the speech recognizer: "Save name, delete <name>, select <name>, delete phone book, yes, no, help".

The commands are clearly linked to the corresponding actions 1903, which are explained in more detail below.

After the command "Save name" has been recognized, the system switches to the second speech dialog state 2 and the phoneme dictionary is loaded. The following voice prompt is also output to the user: "Please speak the name."

If the command "delete <name>" is recognized, then no speech dialog state transition is carried out, but on the one hand the speech prompt: "Do you really want to delete <name>?" are output and both the specification and the command "Delete <name>" are buffered.

If the command "Select <name>" is recognized, the system does not change to another voice dialog state and the following voice prompt is output: "Do you really want to select <name>?" and the information of "<name>" and of "select <name>" are buffered.

After recognizing the command "delete phone book", the first voice dialog state 1 also remains and the voice prompt is output: "Do you really want to delete the phone book?" and the command "delete phone book" is cached. In the event that the "yes" command is recognized, the first speech dialog state 1 also remains, and the command temporarily stored in the buffer with the associated information is executed and, depending on the respective temporarily stored command, file management is started.

For example, in the event that the "delete <name>" command is cached, the cached "<name>" is deleted from the dictionary, that is, the list of names. The basic dictionary is also reloaded.

If the command "select <name>" is temporarily stored, the sequence of digits belonging to the temporarily stored "<name>" is dialed by the telephone, in other words, the actuator controls the telephone in such a way that a communication connection to the subscriber with the associated telephone number is established ,

If the command "delete phone book" is cached, the entire "list", as it is also cached as information, is deleted from the dictionary. The base dictionary is also reloaded.

If the speech recognizer recognizes the command "No", the first speech dialog state is lingered and the memory is initialized as actions and the basic dictionary 1901 is reloaded.

In the event that the "Help" command has been recognized, all commands available in this speech dialog state are graphically presented to the user for selection.

20 shows a speech dialogue state diagram 2000 for a second speech dialogue state 2 according to the second exemplary embodiment of the invention. The available phonemes are stored in the phoneme dictionary 2001, the user-defined entries <name> can be recognized as possible commands 2002 and the action 2003 of a recognized command is intended to remain in the second speech dialog state and to change the number of allowed attempts to increase the value 1, and in the event that the number of permitted attempts has been exceeded, to change to the first speech dialog state 1.

If no utterance is temporarily stored in the buffer in the second speech dialog state, the first phoneme sequence, that is to say the first utterance, is buffered. However, if an utterance has already been buffered in the buffer, the utterance is buffered as a second utterance in the form of a second phoneme chain.

In the event that two utterances have already been cached, the uttered utterance is cached as a third utterance in the form of a third phoneme chain and file management is then started, which carries out the following method steps:

First, the three cached statements are matched. In the event that no match of the three cached utterances is achieved, the request is rejected, the buffer is emptied and the actions of the second speech dialog state 2003 are carried out again.

The two best utterances are then compared with the entries contained in the dictionary. If the similarity in the sense of the above description using the inter-threshold is too great, the request for an additional name in the dictionary is rejected and the buffer is emptied. In In this case, the action 2003 of the second speech dialog state is carried out again.

In the event that a match could not be generated, a check is carried out to determine whether the memory is already fully occupied and, in the event that the memory is fully occupied, the request for the entry of a new user-defined entry in the dictionary is rejected and it is carried out Speech dialog state transition to the first speech dialog state 1 and at the same time the basic dictionary is loaded.

In the event that sufficient free space is available and the above checks have been positive, the desired user-defined entry is added to the dictionary as a list entry. In this case, the best acoustic representation of the entered linguistic utterance is saved as a voice prompt.

This is followed by a voice dialog state transition into the third voice dialog state 3, which is explained in more detail below, while simultaneously loading a number dictionary 2101, more precisely the dictionary which is used in the third voice dialog state 3.

A speech dialog state diagram 2100 of the third speech dialog state is shown in Fig. 21.

The electronic dictionary 2101 of the third speech dialog state 3 has the following entries: "zero, one, two, two, three, four, five, six, seven, eight, nine, save, correction, back, cancel, help".

The following command chains can be recognized and interpreted by the speech recognizer as commands 2102: "<numeric keypad>, save, correction, back, cancel, help". If the command "<number block>" is recognized, the respectively recognized numbers are temporarily stored in the buffer and the speech recognizer remains in the third speech dialog state 3.

If the "Save" command is recognized, the content of the buffer memory is saved in the list of telephone numbers and a speech dialog state transition takes place to the first speech dialog state 1 with simultaneous loading of the basic dictionary.

When the “correction” command is recognized, the last time that the numeric keypad, which is temporarily stored in the buffer, is deleted as action 2103. In addition, the third speech dialog state 3 remains.

When the command “Back” is recognized, the third speech dialog state 3 also remains and the last digit buffered in the buffer is deleted.

When the "Cancel" command is recognized, the system switches to the first speech dialog state 1 while simultaneously loading the basic dictionary.

When the "Help" command is recognized, the user is again presented with all of the commands available in the third speech dialog state 3.

FIG. 22 shows a mobile radio telephone device 2200, in which the speech recognition device 100 shown in FIG. 1 is integrated. Furthermore, a PDA (Personal Digital Assistant) can be integrated into the mobile radio telephone device 2200 as well as further telecommunication functions, such as for example the sending and / or receiving of

Fax messages or SMS messages (Short Message Service messages) or MMS messages (Multimedia Message service messages). Furthermore, the mobile radio telephone device 2200 can be expanded by additional multimedia functionalities, for example a camera can be integrated in the mobile radio telephone device 2200.

Fig. 23 shows a car radio 2300 in which (symbolically shown in Fig. 23) a large number of different components are integrated, for example a navigation system 2301, a CD player 2302, a cassette recorder 2303, a radio 2304, a telephone device with hands-free system 2305 and the speech recognition device 100, as shown in Fig.l. The information can be exchanged between the user and the car radio 2300 both by means of the speech recognition device 100 and via a screen 2306.

The invention is particularly suitable for controlling a system providing a multitude of different functionalities, such as a car radio 2300 provided with a multitude of different functions, since an arbitrarily complicated voice dialog structure can be set up and implemented very flexibly and independently of the speaker.

The following publication is cited in this document:

[1] E.G. Schukat-Talamazzini, Automatic Speech Recognition, Fundamentals, Statistical Models and Efficient Algorithms, Vieweg Verlag, ISBN 3-528-05492-1, pages 121-164, 1995

[2] EP 0 797 185 Bl

[3] DE 695 14 382 T2

LIST OF REFERENCE NUMBERS

100 speech recognition device

101 voice signal

102 microphone

103 Recorded analog voice signal

104 preprocessing

105 Preprocessed voice signal

106 analog / digital converter

107 Digital voice signal

108 computers

109 input interface

110 microprocessor

111 memory

112 output interface

113 computer bus

114 Electronic dictionary

115 keyboard

116 computer mouse

117 cables

118 cables

119 radio connection 120 radio connection

121 speakers

122 actuator

123 DSP

200 speaker-independent dictionary

201 basic entry

202 Speaker dependent dictionary

203 Entry memory-dependent dictionary

204 Common dictionary

300 speech recognizer state diagram 301 initialization state

302 Stop state 303 Pause state 304 operating mode state 305 method step 306 method step 307 method step 308 method step

309 step

310 step

311 procedural step

312 procedural step

313 procedural step

314 procedural step

400 speech dialog state diagram

401 Voice dialog state preceding 402 Voice dialog state X 403 Dictionary 404 word

405 language-dependent list entry

406 command

407 command request 408 action

409 request for action

500 flowchart

501 start state

502 First cycle

503 Second cycle

504 First test step

505 end state

506 Second test step

507 Third test step

508 Third cycle

509 Fourth test step

600 message flow diagram

601 message StartHMMSRFlowgraph

602 confirmation message 603 InitHMMSRParams message

604 confirmation message

605 Message StartLoadHMMLDA

606 Message SMBRequestLoadHMMLDA

607 confirmation message

608 Message StartLoadHMMDictionary

609 Message SMBRequestLoadHMMDictionary

610 confirmation message

611 Message SMBRequestCodebookBlock

612 CodebookBlockLoadedAndSwitched message

613 Message SMBRequestCodebookBlock

614 CodebookBlockLoadedAndSwitched message

615 Message StartHMMSR

616 confirmation message

617 Message SMBRequestCodebookBlock

618 CodebookBlockLoadedAndSwitched message

619 message HMMHypothesisStable 620 confirmation message

621 Message pause HMMSR

622 confirmation message

700 message flow diagram

701 message SetHMMSearchParams

702 confirmation message

703 Message StartLoadHMMDictionary

704 message SMBRequestLoadHMMDictionary 705 confirmation message

706 message StartHMMSR

707 confirmation message

708 Message SMBRequestCodebookBlock

709 Message CodebookBlockLoadedAndSwitched

710 Message HMMHypothesisStable

711 confirmation message

712 Message break HMMSR

713 confirmation message

800 message flow diagram 801 message StartHMMSR

802 confirmation message

803 Message SMBRequestCodebookBlock

804 Message CodebookBlockLoadedAndSwitched

805 Message HMMHypothesisStable

806 confirmation message

807 Message break HMMSR

808 confirmation message

900 functional diagram

1000 function diagram

1100 "Language Prompts" Table

1101 Table "Additional system reactions"

1200 speech dialog state diagram

1201 command

1202 Command request

1203 action

1204 Action request

1205 Action request

1300 Speech dialog state diagram 1310 Flow diagram

1400 Speech dialog state diagram 1410 Flow diagram

1500 Speech dialog state diagram 1510 Flow diagram

1600 Speech dialog state diagram 1610 Flow diagram

1700 Voice dialog state diagram 1710 Flow diagram 1800 speech dialog state diagram 1810 flow diagram

1900 Speech dialog state diagram

1901 dictionary

1902 command list

1903 action list

2000 speech dialog state diagram 2001 interrogation dictionary

2002 command list

2003 action list

2100 speech dialog state diagram

2101 number dictionary

2102 command list

2103 Action list

2200 mobile phone

2300 car radio

2301 navigation system

2302 CD player

2303 radio

2304 tape recorder

2305 phone

2306 screen

Claims

claims 1. Speech recognition device with A speech recognition unit, an electronic dictionary coupled to the speech recognition unit, in which the words taken into account in the context of the speech recognition are stored, A word spacing determination unit for determining the similarity of a first utterance to at least one second utterance in an utterance comparison space, the first utterance and the second utterance each having a sequence of spoken units, A dictionary supplement unit for supplementing the electronic dictionary with the first utterance, depending on the determined similarity of the first utterance with at least the second utterance. 2. Speech recognition device according to claim 1, • in which the word similarity determination unit is a Dictionary similarity determination unit has to determine the similarity of the first utterance with the second utterance, Wherein the second utterance is stored in the electronic dictionary, Wherein the speech recognition device is set up in such a way that the first utterance is only added to the electronic dictionary if the similarity of the first utterance to the second utterance is less than a predetermined first Similarity threshold. 3. Speech recognition device according to claim 1 or 2, In which the word similarity determination unit has an utterance similarity determination unit for Determining the similarity of the first utterance to a third utterance, Wherein the speech recognition device is set up in such a way that the first utterance is only added to the electronic dictionary if the similarity of the first utterance to the third utterance is greater than a predetermined second similarity threshold. 4. Speech recognition device according to one of claims 1 to 3, in which the speech recognition unit is set up for speaker-independent speech recognition 5. Speech recognition device according to one of claims 1 to 4, • with a speech signal imaging unit coupled to the electronic dictionary for imaging the speech signal spoken by a user onto a sequence of spoken units representing the speech signal, • the sequence of spoken units being set up in this way that it can be processed by the speech recognition unit as part of the speaker-independent speech recognition, • the sequence of spoken units representing the first utterance. 6. Speech recognition device according to claim 4 or 5, in which the speech recognition unit is set up in such a way that the speaker-independent speech recognition is based on the following principles: • Speech recognition using hidden Markov models, • Speech recognition using statistical classifiers, in particular using at least one artificial neural network. 7. Speech recognition device according to claim 6, in which the sequence of phonetic units is formed by a phoneme chain. 8. Speech recognition device according to one of claims 1 to 7, set up as an embedded system. 9. Control device for controlling a technical system with a speech recognition device according to one of claims 1 to 8, wherein the control commands provided for controlling the technical system are stored in the electronic dictionary. 10. Telecommunication device with a control device according to claim 9. 11. Method for the computer-aided addition of an electronic dictionary for a speech recognition unit for speech recognition, in which the words taken into account in the context of the speech recognition are stored, In which, for a first utterance, the similarity to at least one second utterance is determined in an utterance comparison space, the first utterance and the second utterance each having a sequence of spoken units, • in which the electronic dictionary is supplemented by the first utterance depending on the determined similarity of the first utterance with at least the second utterance. 12. The method according to claim 11, In which the similarity of the first utterance to the second utterance is determined, the second utterance being stored in the electronic dictionary, • where the first utterance is only added to the electronic dictionary if the similarity of the first utterance to the second utterance is less than a predetermined first similarity threshold. 13. The method according to claim 11 or 12, • in which the similarity of the first utterance to a third utterance is determined, • in which the first utterance is only added to the electronic dictionary if the similarity of the first utterance to the third utterance is greater as a predetermined second similarity threshold. 14. The method as claimed in one of claims 11 to 13, in which, for at least one speech signal spoken by a user, a sequence of spoken units, which represents the speech signal, is formed as the first utterance, the first utterance being set up in such a way that it is generated by the speech recognition unit can be processed as part of a speaker-independent speech recognition 15. The method according to any one of claims 11 to 14, used for speech recognition. 16. The method according to claim 15, used for speaker-independent speech recognition.