JP5235849B2 - Speech recognition apparatus, method and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To reduce processing time of reliability calculation of a voice recognition result. <P>SOLUTION: A prior reliability score calculation section of the voice recognition device sets voice feature quantity sequence for each frame as input, sets difference between an output probability of maximum likelihood state of a mono-phone and that of a voice model or of a pause model as prior reliability of the frame, and outputs a reliability score in which the prior reliability is averaged in a voice file unit. A voice recognition processing section sets the voice feature quantity sequence and the reliability score as input, performs voice recognition processing and outputs a voice recognition result and the reliability score. <P>COPYRIGHT: (C)2011,JPO&amp;INPIT

Description

  The present invention relates to a speech recognition apparatus, method and program for efficiently recognizing speech data of various sound qualities.

  In recent years, it has become possible to easily obtain a large amount of audio data as a memory element for recording audio data becomes cheaper. When recognizing such audio data, there arises a problem that the recognition accuracy and processing time greatly vary depending on the quality of the audio data.

  In view of this, conventionally, a method for suppressing a defect caused by a speech recognition error by giving a reliability to the speech recognition result has been studied. FIG. 11 shows a functional configuration of the speech recognition apparatus 900 configured to give reliability to the speech recognition result. The speech recognition apparatus 900 includes an acoustic analysis unit 120, an acoustic model storage unit 140, a dictionary / language model storage unit 150, a search unit 160, and a reliability calculation unit 190.

  The acoustic analysis unit 120 generates an acoustic feature parameter series 130 by analyzing, for example, a mel frequency cepstrum coefficient (MFCC) of the input speech signal 110 in units called frames of several tens of ms. The search unit 160 searches the recognition result candidates for the acoustic feature parameter series 130 using the acoustic model storage unit 140 and the dictionary / language model storage unit 150. As a result of the search, the N best speech recognition results 170 from the top to the Nth and the score 180 are output.

  The reliability calculation unit 190 calculates and outputs a reliability score 200 corresponding to each of the plurality of speech recognition results 170 based on the speech recognition result 170 and the score 180. The reliability score 200 is obtained from, for example, N best candidates obtained as a result of speech recognition, a simple score difference between these scores, and an addition average.

  By referring to the reliability score 200, the speech recognition result 170 corresponding to the reliability score 200 is discarded, or the recognition result is confirmed with respect to the speaker, so that a malfunction due to misrecognition occurs. It was suppressed.

JP 2005-148342 A

  However, in the conventional speech recognition apparatus 900, the reliability score is calculated from the score after performing the speech recognition processing. Accordingly, it takes time for the speech recognition processing to obtain the reliability score. Therefore, for example, extra processing time may be spent on unusable audio data due to a bad S / N ratio. Also, when performing speech recognition processing on a large number of audio files, it takes time to process an audio file with low speech recognition accuracy, and processing of other audio files with high speech recognition accuracy does not proceed. The processing efficiency may be reduced. Moreover, since the processing is based on the speech recognition result using the language model, there is a problem that the reliability score value depends on the language model.

  The present invention has been made in view of such a problem, and is capable of calculating a reliability score in a short processing time without performing a voice recognition process, and outputting a reliability score independent of a language model. It is an object of the present invention to provide a recognition device, a method thereof, and a program.

The speech recognition apparatus according to the present invention includes a feature amount analysis unit, a prior reliability score calculation unit, and a speech recognition processing unit. The feature amount analysis unit analyzes the speech feature amount of the input speech digital signal in units of frames and outputs a speech feature amount sequence. The prior reliability score calculation unit receives a speech feature amount sequence for each frame as an input, and outputs an output probability of a monophone maximum likelihood state and a speech model (for example, speech GMM, where GMM is a Gaussian Mixture Model, that is, a mixed normal distribution) ) Or a pose model (for example, a pose HMM: Hidden Markov Model) and the difference between the maximum likelihood state output probability (of the GMM contained therein) as the prior reliability of the frame, and the prior reliability in units of audio files. Output the average confidence score. The speech recognition processing unit receives the speech feature amount series and the reliability score and outputs a speech recognition result.

  According to the speech recognition device of the present invention, the prior reliability score calculation unit receives the speech feature value sequence for each frame as an input, and outputs the monophone maximum likelihood state output probability and the speech model or pose model maximum likelihood state output probability. And the difference score is used as the prior reliability of the frame, and a reliability score obtained by averaging the prior reliability in units of audio files is output. Therefore, the reliability score is obtained by processing that is lighter than that of the conventional speech recognition apparatus. Then, by determining whether or not to perform speech recognition processing according to the value of the obtained reliability score, it is possible to solve the problem that it takes time for speech recognition processing of an audio file with low reliability and low speech recognition accuracy. Is done.

The figure which shows typically the relationship between an audio | voice feature-value and likelihood (or output probability) in order to demonstrate the fundamental view of this invention. The figure which shows the function structural example of the speech recognition apparatus 100 of this invention. The figure which shows the operation | movement flow of the speech recognition apparatus 100. The figure which shows the function structural example of the prior reliability score calculation part 30. FIG. The figure which shows typically the time passage of the output probability of a monophone, the output probability of a pause model, and an audio | voice model. The figure which shows the case where FIG. 4 is made into 2 or more types of acoustic models. The figure which shows the function structural example of the speech recognition apparatus 250 of this invention. The figure which shows the example of the relationship between the reliability score C and beam search width | variety N (C). The figure which shows the function structural example of the speech recognition apparatus 300 of this invention. The figure which shows the operation | movement flow of the speech recognition apparatus 300. The figure which shows the function structure of the conventional speech recognition apparatus 900 disclosed by patent document 1. FIG.

Embodiments of the present invention will be described below with reference to the drawings. The same reference numerals are given to the same components in a plurality of drawings, and the description will not be repeated. Prior to the description of the embodiments, the basic concept of the present invention will be described.
[Basic concept of this invention]
FIG. 1 shows the relationship between speech feature values and likelihood. Likelihood is a value that generally represents likelihood, and an output probability value may be substituted. The horizontal axis is the voice feature amount, and the vertical axis is the likelihood. In the figure, the respective distributions of the speech model (broken line) and monophone phoneme models “* -a + *”, “* -i + *”, “* -u + *” included in the acoustic model are shown. A phoneme model is usually composed of a plurality of states, and one state is composed of a mixed distribution composed of a plurality of basis distributions (hereinafter referred to as a mixed distribution including a mixed normal distribution). Here, for simplification, the number of states of the phoneme model is expressed as 1, and the number of mixture distributions is expressed as 1.

Here, the monophone is an environment-independent phoneme model. Compared to an environment-dependent phoneme model (for example, a triphone) having restrictions on the preceding and following phoneme environments, there is no restriction on the preceding and following phonemes, and the number of phoneme models Few. For example, when the number of phonemes is 30, the number of phoneme models in the monophone acoustic model is 30, but the number of triphones is 303 (2700).
For example, the GMM used for the speech model is a mixed normal distribution model, which is a model learned from speech, that is, learning data of all phonemes, so that the distribution has a relatively gentle likelihood value for the speech feature. Distribution. On the other hand, since the monophone is a model learned from the learning data of each phoneme, the likelihood value for the speech feature amount corresponding to the phoneme has a steep distribution.

Therefore, it is possible to determine the reliability of an audio file by comparing the likelihood of an audio model for a certain audio feature quantity and the likelihood of a monophone for the same audio feature quantity. In other words, the likelihood of monophone "* -a + *" to speech features of phonemes a was recorded without being affected by noise O _t ^clean (a) shows a large value. However, the likelihood of the speech model for the same speech feature amount O _t ^clean (a) shows a relatively small value. As a result, there is a difference between those values.

On the other hand, the speech feature quantity O _t ^noisy (a) of the phoneme a recorded under the influence of noise is different from the original feature quantity, so the likelihood in the monophone and the likelihood in the speech model are The difference between is smaller.
Thus, the quality of recorded speech can be evaluated by looking at the difference between the likelihood of the monophone and the likelihood of the speech model for the speech feature. The basic idea of the present invention is to pay attention to this point and obtain the difference between the output probability of the maximum likelihood state of the monophone and the output probability of the speech model as a prior reliability, and obtain a reliability score for each audio file. It is a thing.

  FIG. 2 shows a functional configuration example of the speech recognition apparatus 100 of the present invention. The operation flow is shown in FIG. The speech recognition apparatus 100 includes an A / D conversion unit 10, a feature amount analysis unit 20, a prior reliability score calculation unit 30, a speech recognition processing unit 40, an acoustic model parameter memory 50, a language model parameter memory 60, Are provided. The speech recognition apparatus 100 is realized by reading a predetermined program into a computer configured with, for example, a ROM, a RAM, a CPU, and the like, and executing the program by the CPU.

  The A / D conversion unit 10 converts the audio signal into a discrete value at a sampling frequency of 16 kHz, for example, and converts it into an audio digital signal. Note that when the audio digital signal is directly input, the A / D converter 10 is not necessary.

  The feature amount analysis unit 20 receives the speech digital signal and outputs a speech feature amount sequence for each frame in which, for example, 320 speech digital signals are one frame (20 ms) (step S20). As the audio feature amount, for example, dynamic parameters such as MFCC (Mel-Frequenct Cepstrum Coefficient) 1 to 12 elements, ΔMFCC which is the change amount, power, Δ power, and the like are used. Also, processing such as cepstrum average normalization (CMN) may be performed.

  The prior reliability score calculation unit 30 receives the speech feature value sequence for each frame as an input, and outputs the output probability of the maximum likelihood state of the monophone and the output probability of the maximum likelihood state in the speech model or the pose model (in the GMM). Is used as the prior reliability of the frame, and a reliability score obtained by averaging the prior reliability in units of audio files is output (step S30).

  The speech recognition processing unit 40 refers to the acoustic model recorded in the acoustic model parameter memory 50 and the language model recorded in the language model parameter memory 60, performs speech recognition processing on the speech feature quantity sequence, and the speech A recognition result and a reliability score are output (step S40). Note that the voice recognition processing unit 40 may switch whether or not the voice recognition process is executed according to the reliability score value of the voice file as indicated by a broken line. The voice recognition process in step S40 is repeated until the process is completed for all frames of the voice file.

  According to the speech recognition apparatus 100, the prior reliability score calculation unit 30 assigns a prior reliability to each frame and calculates an average reliability score (calculating an average prior reliability per frame) for each audio file. calculate. The reliability score based on the speech feature amount series requires less calculation amount than the conventional method of obtaining the reliability score from the speech recognition result. In addition, when processing a plurality of audio files, it is determined whether or not to perform the speech recognition processing according to the value of the prior reliability, so that an audio file having a low prior reliability, that is, a speech recognition accuracy is low. The problem that time is required for the speech recognition processing is also solved. Next, a more specific configuration example of the prior reliability score calculation unit 30 that is a main part of the first embodiment will be described and described in more detail.

[Pre-reliability score calculator]
FIG. 4 shows a functional configuration example of the prior reliability score calculation unit 30. The prior reliability score calculation unit 30 includes a monophone maximum likelihood detection unit 32, a pose / voice model maximum likelihood detection unit 33, a prior reliability calculation unit 34, and a reliability score calculation unit 35.
The monophone maximum likelihood detection unit 32 outputs the output probability P (t, s1) of the maximum likelihood state s1 of a plurality of monophones to the speech feature amount sequence input every frame t to the prior reliability calculation unit 34. The pose / speech model maximum likelihood detection unit 33 outputs the output probability P (t, g1) of the maximum likelihood state g1 of the speech model or the pose model for the speech feature quantity sequence to the prior reliability calculation unit 34.

FIG. 5 schematically shows the time course of the output probability of the monophone, the output probability of the pause model, and the speech model. In the horizontal direction, the passage of time is represented by a frame t. The vertical direction represents the state of each of a plurality of monophones (including a pause model) and a sound model for each frame t. For example, each monophone (including the pause model) is composed of three states, and the monophone “* -a + *” is composed of a ₁ , a ₂ , and a ₃ . The black circle represents the maximum likelihood state g1 in the monophone. The state with a hatched circle represents the maximum likelihood state g1 in the pose model and the speech model. When the maximum likelihood state s1 in the monophone matches the maximum likelihood state g1 in the pause model and the speech model (s1 = g1), it is indicated by a black circle.
At time t ₁ , none of the plurality of monophones other than the pose has a maximum likelihood state, and the first state of the pose model is the maximum likelihood state. At time t _2, the same manner in any of a plurality of monophone except pose no maximum likelihood state, a second state of pause model is maximum likelihood state. Time t ₃ is also to both no maximum likelihood state of a plurality of monophone other than the pause, the third state of pause model is maximum likelihood state. Therefore, the times t ₁ to t ₃ are in a non-voice state. At this time, since the maximum likelihood state in the monophone matches the maximum likelihood state in the pause model and the speech model (s1 = g1), the value of the prior reliability at the time is 0.
Time t _4, the audio from that in monophones other than the pose is the third state of "* -a + *" in the maximum likelihood state s1, is a speech model is also the maximum likelihood state g1 and in the pose model and the speech model State. Therefore, in this embodiment, the output probability of the time t ₄ of monophones "* -a + *" of the maximum likelihood state s1, and the difference between the pre-reliability of the output probability of maximum likelihood state g1 of the speech model.
In addition, the time t ₁₉ is, in monophones other than pose "* -i + *" in the second state is the maximum likelihood state s1 of, pose model and the third state is the maximum likelihood state g1 pose model in the voice model It is. In this case, the difference between the output probability of the maximum likelihood state s1 of the monophone “* -i + *” and the output probability of the maximum likelihood state g1 of the pose model is set as the prior reliability. FIG. 5 shows only a part of the time. The length of the audio file is, for example, about several minutes (for example, 30,000 frames).

  As described above, the prior reliability calculation means 34 calculates the difference between the output probability P (t, s1) of the maximum likelihood state of the monophone and the output probability P (t, g1) of the maximum likelihood state of the speech model or the pose model in advance. It outputs to the reliability score calculation means 35 as reliability C (t) (Formula (1)).

  Here, s1 is a mixture distribution having the highest likelihood at the time t among the states (mixed distribution) belonging to the monophone. g1 is a mixture distribution having the highest likelihood at time t in the speech model or the pose model. P (t, s) is the output probability of state s (mixed distribution belonging to) at time t shown in equation (2).

Here, M _s is the number of mixed states s. c _{s, m} is a mixture weight coefficient of the state s distribution m. Note that c _{s, m} is determined by the result of acoustic model learning, and takes a range of 0 ≦ c _{s, m} ≦ 1. For example, if the number of mixtures is 16, the average value is 1/16. N (•) means the output probability of the feature quantity O _t at time t with respect to the (basic) normal distribution with mean μ _{s, m} and variance Σ _{s, m} .
The reliability score calculation means 35 outputs the reliability score C obtained by accumulating the prior reliability C (t) for the duration T (total number of frames) of the audio file and averaging (formula (3)).

  As described above, the prior reliability score calculation unit 30 calculates the reliability score C representing the reliability of the audio file unit by averaging the prior reliability of the frame unit with the total number of frames of the audio file. Since the reliability score C is obtained for each audio file, no elaborate processing is required.

  The speech recognition processing unit 40 receives the speech feature amount sequence output from the feature amount analysis unit 20 and the reliability score C, performs speech recognition processing, and outputs a speech recognition result. At this time, the reliability score C may be output simultaneously. In this speech recognition process, a recognition process using all acoustic models recorded in the acoustic model parameter memory 50 is performed. The voice recognition processing unit 40 may switch whether or not the voice recognition process is executed according to the value of the reliability score C.

The reliability score C may be a value obtained by averaging the prior reliability calculated based on the monophone (including the pause model) and the audio model included in the two or more types of acoustic models in units of audio files. FIG. 6 shows an example of a time course of output probability when two or more kinds of acoustic models are a male acoustic model and a female acoustic model. The prior reliability score calculation unit 30 ′ obtains the output probabilities P _male (t, s 1) and P _female (t, s 1) of the maximum likelihood state of the male and female monophones for the speech feature amount series at each time t. The larger one is the maximum likelihood output probability P (t, s1), and the maximum likelihood output probability P _male (t, g1) and P _female (t, g1) of the male and female speech models or pose models. The larger one is P (t, g1), and the difference (P (t, s1) −P (t, g1)) is obtained as the prior reliability C (t).

That is, the pose / voice model maximum likelihood detection means 33 'calculates the larger of the male and female voice models or the maximum likelihood output probability P _male (t, g1) and P _female (t, g1) of the pose model. P (t, g1). Then, the monophone maximum likelihood detection means 32 'sets the larger one of the maximum likelihood output probability P _male (t, s1) and P _female (t, s1) of the male and female monophones as P (t, s1). Ask. Then, the reliability score calculation unit 35 outputs a value obtained by averaging the prior reliability C (t) by the total number of frames of the audio file as the reliability score C.

  Further, the acoustic model used for the prior reliability score calculation unit 30 ′ may be three or more types. Thus, by using a plurality of types of acoustic models, an effect of improving the accuracy of the reliability score C can be expected even when the subsequent speech recognition processing uses a plurality of acoustic models.

The reliability score C is a value calculated by comparing the output probabilities of the maximum likelihood states of two or more types of speech models or pause models with respect to the speech feature amount series, and limited to monophones of a type having a large output probability. May be. That is, instead of obtaining the maximum likelihood output probabilities P _male (t, s1) and P _female (t, s1) of male and female monophones as in the above example, a speech model or a pose model A method in which a male (female) has a higher output probability than a female (male) may be calculated only for male (female) monophones.
That is, the pose / speech model maximum likelihood detection means 33 "calculates the larger one of the male and female speech models or the maximum likelihood output probability P _male (t, g1) and P _female (t, g1) of the pose model. Then, the monophone maximum likelihood detecting means 32 ″ obtains the output probability P (t, s1) of the maximum likelihood state of one of the monophones by using the determination result as an input. In this example, since the output probabilities of all types of monophones are not calculated, an effect of reducing the amount of calculation can be expected.

FIG. 7 shows a functional configuration example of the speech recognition apparatus 250 of the present invention. The voice recognition device 250 is different from the voice recognition device 100 in that it includes a recognition processing control unit 251. The recognition processing control unit 251 outputs a control signal for stopping the speech recognition processing to the speech recognition processing unit 40 when the reliability score C is equal to or less than a certain value _Cth . Since the reliability score C is a value calculated for each voice file, the voice recognition processing unit 40 switches whether or not the voice recognition process is executed for each voice file. For example, a method of calculating the constant value C _th from the reliability score distribution for the learning data of the acoustic model is conceivable. When the average value μ and the standard deviation σ of the reliability score distribution are used, for example, C _th = μ−2σ. Further, the constant high reliability score value C _const shown in Expression (1) may be C _const = μ + 2σ or the like.

  The recognition processing control unit 251 may output the beam search width N (C) as a control signal. An example is shown in equation (4).

FIG. 8 illustrates the relationship between the reliability score C and the beam search width N (C). The horizontal axis is the reliability score C, and the vertical axis is the beam search width N (C).
As shown in FIG. 8, the equation (4) represents the beam search width N (C) (N _{min to} N _max ) corresponding to the reliability score C (C _{min to} C _max ) in a predetermined range, and the reliability score C It is an idea of proportionally distributing with the value of. Here, since the proportionality coefficient is a negative value, the reliability score C is small and the beam search width N (C) is large, and C is large and N (C) is small. Of course, the relationship between the reliability score C and the beam search width N (C) may be a relationship that can be expressed by a non-linear function. Further, when the beam search width N (C) is used as the control signal, the beam search width is not limited to the number beam width. For example, the score search width, the word end score beam width, the word end number beam width, etc. There may be.
Here, for example, C _max = μ + σ, C _min = μ−σ, N _max may be 1.5 times the beam width normally used, N _min may be half the beam width normally used, and the like. In addition, when the average sound quality is extremely low (for example, C <C _min ), even if the beam search width is increased, the accuracy cannot be improved and it takes much processing time. Therefore, the beam search width is reduced, for example, N _min. good. Further, the speech recognition process may not be performed by including the non-recognition instruction signal in the control signal. Further, a signal for stopping the speech recognition process and a control signal for the beam search width may coexist.

  As described above, the speech recognition apparatus 250 including the recognition processing control unit 251 can improve the efficiency of speech recognition processing for a plurality of speech files and improve the recognition accuracy. Note that the function of the recognition processing control unit 251 may be provided in the voice recognition processing unit 40.

  FIG. 9 shows a functional configuration example of the speech recognition apparatus 300 of the present invention. FIG. 10 shows an operation flow. The voice recognition device 300 is different from the voice recognition devices 100 and 250 in that it includes a voice file processing unit 301 and a sorted voice recognition processing unit 302.

  The audio file processing unit 301 rearranges the plurality of audio files in descending order of the reliability score C of the plurality of audio files (step S301). The sorted speech recognition processing unit 302 performs speech recognition processing in descending order of the reliability score C (step S302).

By executing the speech recognition processing in the order of the reliability score C in this way, it is possible to improve the processing efficiency when performing speech recognition processing of a plurality of speech files. For example, when it is difficult to perform speech recognition processing on all speech files due to the relationship between computer resources and processing time, speech recognition processing is not performed on speech files having a low reliability score C, and speech recognition accuracy is high. The voice recognition process is performed only on a voice file having a high reliability score C that is expected to be high, and it is possible to collect a highly accurate voice recognition result. Note that the function of the voice file processing unit 301 may be included in the function of the sort voice recognition processing unit 302.
As described above, according to the speech recognition apparatus of the present invention, the prior reliability based on the speech feature amount series is obtained, and the reliability score obtained by averaging the prior reliability for each audio file is calculated. Therefore, the reliability score is obtained by processing that is lighter than that of the conventional speech recognition apparatus. Further, since the processing is based on the voice feature amount, a reliability score independent of the language model can be obtained. Further, by determining whether or not to perform the voice recognition process according to the value of the obtained reliability score, for example, the voice recognition process of the voice file with low voice recognition accuracy due to a reason such as a poor S / N ratio. It can solve the problem that takes time.

Note that the processes described in the above method and apparatus are not only executed in time series according to the order of description, but may also be executed in parallel or individually as required by the processing capability of the apparatus that executes the processes. Good.

  Further, when the processing means in the above apparatus is realized by a computer, the processing contents of functions that each apparatus should have are described by a program. Then, by executing this program on the computer, the processing means in each apparatus is realized on the computer.

  The program describing the processing contents can be recorded on a computer-readable recording medium. As the computer-readable recording medium, any recording medium such as a magnetic recording device, an optical disk, a magneto-optical recording medium, and a semiconductor memory may be used. Specifically, for example, as a magnetic recording device, a hard disk device, a flexible disk, a magnetic tape or the like, and as an optical disk, a DVD (Digital Versatile Disc), a DVD-RAM (Random Access Memory), a CD-ROM (Compact Disc Read Only). Memory), CD-R (Recordable) / RW (ReWritable), etc., magneto-optical recording medium, MO (Magneto Optical disc), etc., semiconductor memory, EEP-ROM (Electronically Erasable and Programmable-Read Only Memory), etc. Can be used.

  The program is distributed by selling, transferring, or lending a portable recording medium such as a DVD or CD-ROM in which the program is recorded. Further, the program may be distributed by storing the program in a recording device of a server computer and transferring the program from the server computer to another computer via a network.

  Each means may be configured by executing a predetermined program on a computer, or at least a part of these processing contents may be realized by hardware.

Claims (7)

A feature amount analysis unit that analyzes a speech feature amount of an input speech digital signal in units of frames and outputs a speech feature amount sequence;
With the speech feature value sequence for each frame as an input, the difference between the output probability of the maximum likelihood state of the monophone and the output probability of the maximum likelihood state of the speech model or the pose model is defined as the prior reliability of the frame, and the prior reliability is defined as A prior reliability score calculator that outputs an average reliability score for each audio file;
A speech recognition processing unit that performs speech recognition processing using the speech feature amount sequence and the reliability score as inputs;
A speech recognition apparatus comprising: The speech recognition apparatus according to claim 1,
The speech recognition apparatus, wherein the reliability score is a value obtained by averaging prior reliability based on two or more kinds of acoustic models in units of audio files. The speech recognition apparatus according to claim 1,
The prior reliability is obtained by comparing the output probabilities of the maximum likelihood states of a speech model or a pose model among two or more types of acoustic models for the speech feature amount series, and limited to the acoustic model having the maximum output probability. The difference between the output probability of the monophone calculated in the above and the output probability of the maximum likelihood state of the speech model or the pose model in the acoustic model in the maximum type of acoustic model,
A voice recognition device characterized by the above. The speech recognition apparatus according to any one of claims 1 to 3,
As input on relaxin Yoriyukido score, the recognition control unit for outputting to the voice recognition processing unit and generates a control signal for selecting a voice file to be speech recognition process,
The speech recognition apparatus further comprising: The speech recognition apparatus according to any one of claims 1 to 3,
A voice file processing unit for rearranging the plurality of audio files in descending order of on connexin Yoriyukido scores of the plurality of audio files,
A sorted speech recognition processing unit that performs speech recognition processing in the order of high reliability score ;
A speech recognition apparatus, further comprising: A feature amount analysis unit that analyzes a speech feature amount of an input speech digital signal in units of frames and outputs a speech feature amount sequence; and
The prior reliability score calculation unit receives the speech feature quantity sequence for each frame as an input, and calculates the difference between the output probability of the maximum likelihood state of the monophone and the output probability of the maximum likelihood state of the speech model or the pose model. Pre-reliability score calculation process that outputs a reliability score that is the reliability and averages the prior reliability for each audio file,
A speech recognition processing section in which a speech recognition processing unit performs speech recognition processing using the speech feature amount sequence and the reliability score as inputs;
A speech recognition method including: Program for causing a computer to function as a speech recognition apparatus according to any one of claims 1 to 4.

Images