JP2003108180A - Method and device for voice synthesis - Google Patents

Abstract

PROBLEM TO BE SOLVED: To obtain a voice synthesis result of high quality by performing voice synthesis processing after optimizing parameters used for the voice synthesis so as to obtain the voice synthesis result of high quality. SOLUTION: A voice synthesizing device 1 inputs a text, synthesizes a voice of the text, and outputs a voice signal, a voice recognizing device 2 recognizes the voice signal outputted from the voice synthesizing device 1 and outputs its voice recognition result as a text, and a text comparison part 3 compares the text as the voice recognition result with the text inputted to the voice synthesizing device 1. The text comparison part 3 supplies the comparison result to the voice synthesizing device 1 and the voice synthesizing device 1 obtains optimum parameters by changing the parameters for the voice synthesis until a signal indicating matching is received and outputs the voice signal obtained by performing voice synthesis according to the optimum parameters as the voice synthesis result.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a voice synthesizing method and a voice synthesizing apparatus for generating a voice signal from text.

[0002]

2. Description of the Related Art Speech rule synthesis for generating a speech signal from a given text has been widely used in the past as an information processing technology for handling speech. Here, this speech rule synthesis will be simply referred to as speech synthesis.

Recently, due to advances in speech synthesis techniques,
It is becoming possible to generate more natural synthetic speech, but there is still room for improvement in appropriately expressing the content of the text and the situation on the spot and generating synthetic speech close to the human voice.

[0004]

Briefly speaking, this speech synthesis is performed by subjecting an input text to language processing using a language dictionary and language parameters, converting it into reading information (pronunciation information), and further The phonetic information is processed by using the phoneme dictionary and the prosodic parameters to generate a voice signal, but the generated voice signal often does not properly reflect the content of the text.

For example, when a character string such as "800F" (in this case, the reading is "Happyakuefu") is present in the input text, the text is subjected to the above-mentioned procedure. When synthesizing voice,
Interpret "F" of "800F" as "floor",
In some cases, an audio signal such as "Happyakai" is output. Further, there is also a problem that the accent cannot be properly judged and, for example, "hashi" is output as a voice signal of the accent of "chopsticks".

In order to deal with such a problem, a method of automatically evaluating a voice synthesis result and making a correction to obtain a proper voice synthesis result based on the evaluation result has been considered. However, especially in the case of Japanese, since the language processing is complicated, it is difficult to automatically and objectively evaluate the speech synthesis result and make a correction to obtain an appropriate speech synthesis result.

Therefore, the present invention provides a voice synthesizing method and apparatus capable of performing voice synthesizing processing by performing learning so as to obtain an optimum voice synthesizing result when voice synthesizing text to generate a voice signal. It is intended to be provided.

[0008]

In order to achieve the above object, a speech synthesis method of the present invention is such that a text is input to a speech synthesis means and the text is subjected to speech synthesis processing using parameters necessary for speech synthesis. Output as a voice signal, voice-recognize the voice signal, compare the text as the voice recognition result with the text input to the voice synthesizing means, and set the parameter to a certain value based on the comparison result. Then, it is used as a learning parameter, and a voice signal obtained by performing voice synthesis with the learning parameter is output as a voice synthesis result.

In this voice synthesizing method, the process of setting the parameter to a certain value based on the comparison result and using it as a learning parameter is performed by the text as the voice recognition result being input to the voice synthesizing means. This is a process in which the parameter is changed until it matches with, and the parameter when both match is the learning parameter.
Then, the learning parameters can be saved.

Further, according to the voice synthesis method of the present invention, when a text is input to the voice synthesis means and the text is subjected to the voice synthesis processing using the parameters necessary for the voice synthesis, when there are a plurality of candidates as the parameters. , Selecting a parameter from the plurality of candidates, performing speech synthesis using the selected parameter, recognizing the speech synthesis result, and recognizing the speech recognition result and the text input to the speech synthesis means. Is determined, and one of the parameters of the plurality of candidates is selected based on the result of the similarity determination, the selected parameter is set as a learning parameter, and the speech is synthesized by the learning parameter. The obtained voice signal is output as a voice synthesis result.

In this speech synthesizing method, in the process of selecting one of the parameters of the plurality of candidates based on the similarity determination result and using the selected parameter as a learning parameter, the similarity is predetermined. This is a process in which the candidate parameters are sequentially selected until the value becomes equal to or more than a value, and the parameter whose similarity becomes equal to or more than a predetermined value is used as a learning parameter. Then, the learning parameters can be saved.

The speech synthesizer of the present invention further comprises a speech synthesizing means for inputting text, subjecting the text to speech synthesis processing using parameters necessary for performing speech synthesis, and outputting the speech signal as a speech signal. A voice recognition means for voice-recognizing a voice signal output from the means and outputting the voice recognition result as text, and a text for comparing the text as the recognition result by the voice recognition means with the text input to the voice synthesis means. Comparing means, wherein the speech synthesizing means sets the parameter to a certain value based on a comparison result between the text as the recognition result output from the text comparing means and the text input to the speech synthesizing means. Then, it is used as a learning parameter, and the speech signal obtained by speech synthesis with the learning parameter is used as the speech synthesis result. It is to be output.

In this speech synthesizer, the process of setting the parameter to a certain value on the basis of the comparison result and using it as a learning parameter is such that the text as the recognition result output from the text comparing means is the voice. This is a process in which the parameters are changed until they match the text input to the synthesizing means, and the parameters when both match are used as learning parameters.

The voice synthesizing means is provided with a parameter storing means, and the pre-learning parameters can be stored in the parameter storing means.

In the speech synthesizer of the present invention, when a text is input to the speech synthesis means and the text is speech-synthesized using the parameters necessary for speech synthesis, if there are a plurality of candidates for the parameter. , A voice synthesizing means for selecting a certain parameter from the plurality of candidates, performing a voice synthesizing process using the selected parameter and outputting as a voice signal, and a voice recognition of the voice signal output from the voice synthesizing means. A voice recognition unit capable of determining the similarity between the recognition result and the text input to the voice synthesizing unit and outputting the similarity determination result,
The voice synthesizing means selects one of the plurality of candidates as a learning parameter based on the similarity determination result from the voice recognizing means, and synthesizes the voice by the learning parameter. The obtained voice signal is output as a voice synthesis result.

The process of selecting any one of the plurality of candidates based on the similarity determination result and using the selected parameter as a learning parameter is performed until the similarity becomes equal to or more than a predetermined value. This is a process in which the candidate parameters are sequentially selected, and the parameters whose similarity becomes a predetermined value or more are used as learning parameters.

Further, the voice synthesizing means is provided with a parameter storing means, and the learning parameters can be stored in the parameter storing means.

As described above, according to the present invention, the text is subjected to the voice synthesis processing using the parameters necessary for the voice synthesis and output as the voice signal, the voice signal is voice-recognized, and the text as the voice recognition result is input. Different texts are compared, and the parameter is changed until the text as the voice recognition result and the text input to the voice synthesizing means match. Therefore, the optimum parameter for the input text is set as the learning parameter. Can be set. This makes it possible to obtain a high-quality speech synthesis result for the input text.

Further, by storing the parameters at that time, it is possible to perform proper voice synthesis only by referring to the same text in subsequent voice synthesis processing if the text is the same.

Further, the present invention is also applied to the case where when there are a plurality of candidates as parameters, one of the plurality of candidates is selected and speech synthesis is performed using the selected parameters. can do. Also in the present invention, as described above, the optimum parameter for the input text can be set as a learning parameter, so that a high-quality speech synthesis result can be obtained for the input text.

Further, in this case, since the process of selecting the optimum parameter from the plurality of candidates is performed, a great effect is exerted particularly in the case of synthesizing a word or the like whose pronunciation or accent is difficult to be determined. In this case as well, since the optimum parameters are stored, proper speech synthesis can be performed by simply referring to the same text in subsequent speech synthesis processing if the text is the same.

[0022]

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of the present invention will be described below. Here, the following two embodiments will be described.

[First Embodiment] FIG. 1 shows a basic configuration for explaining a first embodiment of a voice synthesizing method and a voice synthesizing apparatus according to the present invention. It is composed of a device 2 and a text comparison unit 3.

The processing procedure in the first embodiment will be roughly described. A text to be voice-synthesized (referred to as input text) is subjected to voice-synthesizing processing by the voice-synthesizing device 2 using parameters necessary for voice-synthesizing. , And outputs a voice signal which is the result of the voice synthesis. Then, this voice signal is voice-recognized by the voice recognition device 2 and a text (referred to as output text) as the recognition result is output, and the output text as the recognition result and the input text are compared by the text comparison unit 3. Then, this comparison result is fed back to the voice synthesizing device 1, and the voice synthesizing device 1 outputs a procedure for changing the parameters for performing voice synthesizing and performing the voice synthesizing process again for different portions of the output text with respect to the input text. The process is performed until the text matches the input text, and when the two match, the parameter at that time is used as a learning parameter, and the voice signal obtained by voice synthesis using the learning parameter is output as the voice synthesis result. The details will be described below.

FIG. 2 illustrates FIG. 1 in more detail.
The speech synthesizer 1 includes a language processing unit 11, a language dictionary unit 12,
Phoneme processing unit 13, phoneme dictionary unit 14, parameter generation unit 1
5 and so on. The parameters generated by the parameter generation unit 15 include a language parameter that determines reading of a character string that constitutes a text and sentence separation, and a prosody parameter that determines accents, fundamental frequencies, utterance durations, and the like. , The language parameter is the language processing unit 1
1 and the prosody parameter is given to the phoneme processing unit 13.

The voice recognition device 2 has a voice recognition processing unit 21, which converts an input voice signal into text and outputs the text. The voice recognition processing unit 21 used here is a voice recognition unique to the present invention. Although the method is not used, it is assumed that it has a high recognition performance that can perform ideal recognition for the input speech signal, and the recognition result is a text comparison (text output). Given to part 3.

In such a configuration, the speech synthesizer 1
When the input text is given to, the language processing unit 11
The linguistic dictionary 12 is referred to, and language processing is performed using the language parameter generated by the parameter generation unit 15 to output reading information (pronunciation notation information), and the reading information is given to the phonological processing unit 13. To be The phonological processing unit 13 refers to the phonological dictionary 14 and performs phonological processing using the prosody parameters generated by the parameter generation unit 15 to output a voice signal.

The voice signal output from the phoneme processing unit 13 is given to the voice recognition device 2, and the voice recognition processing unit 21.
The voice recognition process is performed by the text recognition processing, and the text (output text) as the recognition result is output.
Given to.

In the speech recognition processing here, for example, the speech recognition processing is performed by using a speech recognition dictionary and the like in consideration of contexts before and after, and as a recognition result, several recognition candidates are sequentially output from the top. Is output, the first
The recognition candidate of rank is given to the text comparison unit 3 as a recognition result, and the recognition candidate of the first rank is compared with the input text.

The text comparison unit 3 compares the output text output from the voice recognition device 2 and the input text input to the voice synthesis device 1 as a character string to determine whether there is a different portion, If there is a different portion, the parameter generation unit 15 is notified of information indicating the different portion.

When the parameter generation unit 15 receives the information indicating the different portion from the text comparison unit 3, the parameter generation unit 15 generates a parameter different from the previous one, performs the voice synthesis processing by the parameter, and outputs the voice signal as the voice synthesis result. Is output.

Then, the voice signal generated by the parameter different from the last time is input to the voice recognition device 2, the voice recognition process is performed again, and the text as the recognition result (output text) is input to the text comparison unit 3. Given. The text comparison unit 3 compares the output text with the input text and, if there is a different portion, provides the parameter generation unit 15 with information indicating the different portion.

When the parameter generation unit 15 receives the information indicating the different portion from the text comparison unit 3, the parameter generation unit 15 generates a different parameter from the previous time, performs the voice synthesis processing by the parameter, and outputs the voice signal as the voice synthesis result. Is output.

When the output text matches the input text as a result of the comparison between the output text as the voice recognition result and the input text input to the speech synthesizer 1 by repeating the above processing, the text comparing unit 3 matches the output text. A signal is output and the coincidence signal is given to the parameter generation unit 15.

When the parameter generator 15 receives this coincidence signal, it outputs a voice signal as a voice synthesis result at that time to the outside. The parameter at this time is a learned parameter (referred to as a learning parameter) that enables optimal speech synthesis for the input text. Therefore, the speech synthesis result obtained by the speech synthesis processing using the learning parameter can be the optimal speech synthesis result for the input text.

That is, the voice signal obtained by the voice synthesizing process by the voice synthesizing device 1 is voice-recognized by the voice recognizing device 2, and the text output as the recognition result is the same as the text input to the voice synthesizing device 1. If they are the same, it can be said that proper speech synthesis processing has been performed, and the speech synthesis result at that time can be said to be the optimal speech synthesis result for the input text.

FIG. 3 shows an example of the input text and the output text. The input text as shown in FIG. 3A is given to the voice synthesizing device 1, and the voice synthesizing device 1 performs the voice synthesizing process. It is assumed that a voice signal as a voice synthesis result for the input text is output, and the voice recognition device 2 recognizes the voice signal to obtain a text (output text) as shown in FIG. 3B.

In the output text shown in FIG. 3B, the underlined portion is different from the input text. In the example of FIG. 3, the output text corresponding to the input text "issued to the computer ..." is "8000 issued to the computer ...
・, And the part of "I was issued" is "8000 was given".

In other words, in this example, since the "emitted" portion is not properly synthesized into a voice signal and is output as a voice signal "squashed", the voice recognition device 2 "squeezed" the portion. It is recognized as it is, and the text as the recognition result is “8000”.

Therefore, the text comparison unit 3 notifies the parameter generation unit 15 of the information indicating the different portion, so that the parameter generation unit 15 causes the parameter generation unit 15 to change a parameter (phoneme for reading) different from the last time. (Selection, fundamental frequency, accent, utterance duration, etc.) are generated and the parameters are sent to the language processing unit 11 and the prosody processing unit 13.

As a result, the input text "Sent" to the computer ...
The voice synthesis processing is performed again on the part of using the new parameter, and the voice signal as the voice synthesis result is output. This voice signal is input to the voice recognition device 2, a text (output text) as a recognition result is output, and the text comparison unit 3 again compares it with the input text.

If it is determined as a result of the comparison that they match each other, the parameter at that time becomes a learning parameter, and a voice signal obtained by voice synthesis by the learning parameter is output as a voice synthesis result. To be done.

As described above, according to the first embodiment, the text (input text) is subjected to the voice synthesizing process by the voice synthesizing device 1, and the voice signal as the voice synthesizing result is sent to the voice recognizing device 2. It gives voice recognition, compares the recognition result text (output text) with the input text, and if there is a different part in the output text with respect to the input text, use that part with a different parameter from the previous time. A process of performing voice synthesis processing again, giving a voice signal as the voice synthesis result to the voice recognition device 1 to perform voice recognition, and comparing the text (output text) as the recognition result with the input text is called output text. Until the input text matches.

When the output text matches the input text, the speech signal obtained by speech synthesis with the parameter (learning parameter) at that time is output as the speech synthesis result. This makes it possible to obtain the optimum speech synthesis result for the input text at that time.

As described above, the voice signal obtained by the voice synthesizing process by the voice synthesizing device 1 is voice-recognized by the voice recognizing device 2, and the text output as the recognition result is input to the voice synthesizing device 1. The fact that it is the same as the text means that proper speech synthesis processing has been performed. Moreover, the fact that the synthesized speech obtained by speech synthesis is correctly recognized means that the synthesized speech is human-readable. This means that it is a high-quality synthetic speech that has high intelligibility.

In the first embodiment, the learning parameter can be saved. FIG. 4 shows the structure of the speech synthesizer having the function of storing the learning parameters. The parameter storage unit 16 is added to the structure of FIG. 2 and the other parts are the same as those of FIG. The same parts are designated by the same reference numerals.

By thus providing the parameter storage unit 16, the parameter (learning parameter) when the output text matches the input text is stored in the parameter storage unit 16.

As a result, the parameter storage unit 16 accumulates the parameters for obtaining the optimum speech synthesis result for the various texts input so far. Therefore, when the same text is subsequently input, if the voice synthesis is performed using the parameter corresponding to the text, the optimum voice synthesis result for the text can be obtained. Moreover, in that case, the process of generating the learning parameter as described above can be omitted.

[Second Embodiment] FIG. 5 shows a second embodiment of the present invention.
Is a configuration diagram for explaining the embodiment of the present invention, and is similar to the above-described first embodiment in that the second embodiment also has a voice synthesizing device 1 and a voice recognizing device 2.

As in FIG. 2, the speech synthesizer 1 has a language processing unit 11, a language dictionary unit 12, a phoneme processing unit 13, and a phoneme dictionary unit 1.
4 has a parameter generation unit 15, and the second embodiment also has a parameter selection unit 17.

Further, the voice recognition device 2 has a voice recognition processing section 21 similar to that of the first embodiment. The voice recognition processing section 21 performs voice recognition and outputs a recognition result. In this embodiment, the voice recognition processing unit 2
1. The similarity determination unit 2 that determines the similarity between the recognition result in 1 and the input text (text input to the speech synthesizer 1)
Have two.

The second embodiment is a speech synthesizer 1
When performing speech synthesis processing, there are a plurality of parameter candidates required for speech synthesis, and the recognition result of the speech recognition device 2 is used as means for determining the optimum parameter from the plurality of parameters. Note that, as an example in which there are a plurality of parameter candidates necessary for performing voice synthesis, for example, there is a case where the reading or accent of the input text cannot be determined. This will be described below with reference to a specific example.

For example, "... is a new product A-800
Input text such as "I developed F" is the speech synthesizer 1.
Consider the case where it is input to. Here, the speech synthesizer 1
Has a parameter selection unit 17 capable of sequentially selecting a plurality of candidates as a parameter for performing voice synthesis,
It is assumed that the parameter selecting unit 17 selects, from the parameter generating unit 15, for example, a parameter for reading "kai" as the first candidate of the reading parameter for the "F" portion of "800F".

As a result, the synthesized speech output from the speech synthesizer 1 becomes "Happikaku", and the corresponding speech signal is given to the speech recognizer 2. In the voice recognition device 2, the voice recognition processing unit 21 performs voice recognition processing on an input voice signal by using a voice recognition dictionary and the like in consideration of contexts before and after, and outputs the recognition result in order from the top. Several recognition candidates and their similarities are output.

FIG. 6A shows an example of the top several recognition candidates obtained for the voice signal "Happyakukai" and their similarity. In this example, the first recognition is performed. The candidate is “800 times” and its similarity is “43”, the second recognition candidate is “800 floor” and its similarity is “30”, the third.
"100 times" and its similarity "22" as recognition candidates for rank
In this way, the recognition candidates and their similarities are output in order from the first rank.

The degree of similarity here is a numerical value indicating the degree of certainty of the recognition candidate obtained for the input voice signal, and here, "1".
00 "is the maximum. For example, a recognition candidate “800 times” has a certainty “43” with respect to a voice signal “Happyakukai”.

By the way, the recognition result by the voice recognition processing unit 21 (several high-ranking recognition candidates and their similarity) as shown in FIG. 6A is given to the similarity determination unit 22, and this similarity is calculated. The input text input to the voice synthesizer 1 is given to the determination unit 22.

Therefore, the similarity determination section 22 selects one of the top several recognition candidates based on the input text, based on the contexts before and after, and determines the similarity to the selected recognition candidate as the similarity determination result. And outputs it to the parameter selection unit 17.

That is, in this case, the input text is ".
.. The company has developed a new product A-800F. "
Based on the contexts before and after FIG.
Among the top several recognition candidates shown in (a), the second recognition candidate “800th floor” is selected and the similarity “3” is selected.
0 ”is given to the parameter selection unit 17.

The parameter selection unit 17 determines whether or not the degree of similarity has reached a predetermined value. In this case, since the degree of similarity is as low as "30", it has reached a predetermined value. It is determined not to. As a result, the parameter selection unit 17 selects the second candidate of the reading parameter for the portion of “800F”, and here, the parameter for generating the synthetic voice “Happyakuef” is selected as the second candidate. Suppose you have selected.

As a result, the synthesized speech output from the speech synthesizer 1 becomes "Happyakufu", the corresponding speech signal is given to the speech recognition apparatus 2, and the speech recognition processing unit 21 recognizes the speech. Then, as the recognition result, some of the top recognition candidates as shown in FIG. 6B and the degrees of similarity thereof are output, and the output is given to the similarity determination unit 22.

In the example of FIG. 6B, the first recognition candidate is “800F” and its similarity is “80”, and the second recognition candidate is “100F” and its similarity is “22”. Then, the recognition candidates and their similarity are sequentially output from the first rank and are given to the similarity determination unit 22.

In the similarity determination section 22, based on the input text input to the speech synthesizer 1, from the context before and after, etc.,
One of the top several recognition candidates is selected, and the similarity to the selected recognition candidate is given to the parameter selection unit 17 as a similarity determination result.

That is, in this case, the input text is ".
.. The company has developed a new product A-800F. "
The similarity determination unit 22 recognizes the “800F” portion of the text as a recognition result, and then, based on the contexts before and after the text, FIG.
Among the upper recognition candidates shown in (b), “800F” which is the first recognition candidate is selected, and the similarity “80” is given to the parameter selection unit 17.

The parameter selection unit 17 determines whether or not the degree of similarity has reached a predetermined value, and in this case, the degree of similarity is a high value of "80" and has reached a predetermined value. Is determined.

As a result, the parameter selection unit 17 sets the parameter (second candidate) at that time as the correct answer, sets the parameter as the learning parameter, and the speech signal obtained by the speech synthesis by the learning parameter is set as the speech synthesis result. Output.

As another example, for example, "...
If an input text such as "a long bridge over the river ..." is given to the speech synthesizer 1, the speech synthesizer 1 cannot determine the position of the accent with respect to the "bridge", and Consider a case in which a plurality of candidates are output as a parameter expressing the accent for the part.

First, as a first candidate, when a parameter such that "ha" has an accent is given, the speech signal as a speech synthesis result corresponds to "hashi" where "ha" has an accent. An audio signal will be output.

When the speech recognition processing unit 21 considers the context before and after, and performs speech recognition processing using a speech recognition dictionary or the like, the speech signal corresponding to "Hashi" having an accent in "Ha" is As a recognition result,
Similar to the example of "Happyakufu" described above, the top several recognition candidates and their similarities are output.

The top several recognition candidates and their similarities are given to the similarity judging section 22, and based on the input text,
One of the recognition candidates and its similarity are selected, and the similarity to the selected recognition candidate is output as the similarity determination result.

Here, the similarity determination unit 22 selects "bridge" from the top several recognition candidates as a recognition candidate based on the input text. As a result, the similarity of the “bridge” (assuming that the similarity is “40”) is given to the parameter selection unit 17 as the similarity determination result.

In the parameter selection unit 17, the similarity determination unit 2
The degree of similarity “4
It is determined that "0" has not reached the predetermined value, and another parameter is selected as the second candidate.

Here, if a parameter having an accent on "shi" of "hashi" is selected as the second candidate, the speech synthesis processing is performed by the parameter of the second candidate, and the result is generated. The voice signal is provided to the voice recognition device 2.

In other words, in this case, the voice signal as the voice synthesis result is the voice signal corresponding to "hashi" having the accent "shi".

The speech recognition processing section 21 similarly performs speech recognition, and outputs some of the top several recognition candidates and their similarities as the recognition result. The output is given to the similarity judgment section 22 and the input text is output. Based on this, one of the recognition candidates and its similarity is selected, and the similarity to the selected recognition candidate is output as the similarity determination result.

Here, the similarity determination unit 22 selects "bridge" from the top several recognition candidates as a recognition candidate based on the input text. As a result, the similarity of the “bridge” (assuming that the similarity is “90”) is given to the parameter selection unit 17 as the similarity determination result.

In the parameter selection unit 17, the similarity determination unit 2
The degree of similarity “9
It is determined that “0” is higher than a predetermined value, the parameter of the second candidate is used as a learning parameter, and a voice signal obtained by performing voice synthesis using the learning parameter is output as a voice synthesis result.

As described above, in the second embodiment, when a text for which the reading or accent position cannot be determined by the speech synthesizer 1 is input, the parameters for the undetermined portion are selected as some candidates. , Speech synthesis is performed for each candidate, the speech signal that is the result of the speech synthesis is subjected to speech recognition processing, and the top several recognition candidates and their similarity are output as the recognition result. The similarity determining unit 22 selects the similarity corresponding to any of the recognition candidates based on the input text from the similarities corresponding to the similarity, and selects the optimum parameter from the magnitude of the similarity. There is.

As described above, in the voice synthesizing apparatus 1, for the time being, voice synthesis is performed using the parameters selected as candidates,
The voice synthesis result is given to the voice recognition device 2, and it is determined whether or not the parameter is appropriate based on the similarity sent from the voice recognition device 2 side, and the similarity of a predetermined value is obtained. Until then, the process is repeated, and if a similarity of a predetermined value is obtained, the parameter is set as the correct answer.

Then, a voice signal obtained by performing voice synthesis using the determined parameter (learning parameter) is output as a voice synthesis result.

As a result, even if the word is unknown to the speech synthesizer 1, if the speech can be recognized, the optimum speech synthesis result for the input text can be generated.

In the second embodiment, the learning parameter can be stored as in the first embodiment. FIG. 7 shows the configuration of a speech synthesizer having a function of storing this learning parameter.
The configuration shown in FIG. 5 is the same as that of FIG. 5 except that the parameter storage unit 16 is added, and the same portions are denoted by the same reference numerals.

As described above, the learning parameters obtained by the above-described processing are stored in the parameter storage unit 16, so that the parameter storage unit 16 can optimally perform speech synthesis for various texts input so far. The parameters for which the result can be obtained are accumulated. Therefore,
When the same text is subsequently input, if the speech synthesis is performed using the parameter corresponding to the text, the optimal speech synthesis result can be obtained for the text. Moreover, in that case, the process of generating the learning parameter as described above can be omitted.

The present invention is not limited to the embodiments described above, and various modifications can be made without departing from the gist of the present invention. For example, in the above-described second embodiment, the top several recognition candidates and their similarities are output as the voice recognition result, and the similarity determination unit 22 is selected from the plurality of recognition candidates and the corresponding similarities. Selects the similarity corresponding to any of the recognition candidates based on the input text, but if the input text is given to the speech recognition processing unit 21,
Since the voice recognition processing unit 21 can know the correct answer as the voice recognition result, the process of obtaining a number of recognition candidates for the input voice signal and calculating the similarity or arranging the similarity from the top of the similarity is omitted. be able to. This simplifies the processing required for voice recognition, enables high-speed recognition processing, and speeds up the overall processing. In that case, the similarity determination unit 22 is not particularly necessary, and the similarity as the voice recognition result is directly calculated by the parameter selection unit 17.
Can be given to.

Further, according to the present invention, a processing program in which a processing procedure for realizing the above-described present invention is described is created, and the processing program is recorded in a recording medium such as a floppy disk, an optical disk, a hard disk. The present invention also includes a recording medium in which the processing program is recorded. Further, the processing program may be obtained from the network.

[0086]

As described above, according to the present invention, the text is subjected to the voice synthesis processing using the parameters necessary for the voice synthesis and output as a voice signal, the voice signal is voice-recognized, and the voice recognition result is obtained. Is compared with the input text, and the parameter is changed until the text as the voice recognition result and the text input to the voice synthesizing means match, so that it is optimal for the input text. Various parameters can be set as learning parameters. This makes it possible to obtain a high-quality speech synthesis result for the input text.

Further, by storing the parameters at that time, it is possible to perform proper speech synthesis only by referring to the same text in the subsequent speech synthesis processing if the text is the same.

The present invention is also applied to the case where, when a plurality of candidates exist as parameters, one of the plurality of candidates is selected and speech synthesis is performed using the selected parameters. can do. Also in the present invention, as described above, the optimum parameter for the input text can be set as a learning parameter, so that a high-quality speech synthesis result can be obtained for the input text.

Further, in this case, since the process of selecting the optimum parameter from the plurality of candidates is performed, a great effect is exerted particularly in the case of synthesizing a word or the like whose pronunciation or accent is difficult to be determined. In this case as well, since the optimum parameters are stored, proper speech synthesis can be performed by simply referring to the same text in subsequent speech synthesis processing if the text is the same.

[Brief description of drawings]

FIG. 1 is a first speech synthesis method and apparatus according to the present invention.
It is a basic block diagram for explaining the embodiment of.

FIG. 2 is a diagram illustrating the configuration of FIG. 1 in detail.

FIG. 3 is a diagram showing an example of an input text and an output text for explaining the first embodiment.

FIG. 4 is a configuration diagram in which a parameter storage unit for storing a learning parameter is provided in FIG.

FIG. 5 is a second speech synthesis method and apparatus according to the present invention.
It is a block diagram explaining the embodiment of.

FIG. 6 is a voice recognition processing unit 21 according to the second embodiment.
It is a figure which shows the example of the high-order recognition candidate and its similarity which were output from (a), and an input speech signal is "Happyakukai".
Is a diagram showing an example of some top recognition candidates and their similarity, (b) is an example of some top recognition candidates and their similarity when the input speech signal is "Happyakuefu" FIG.

7 is a configuration diagram in which a parameter storage unit for storing learning parameters is provided in FIG.

[Explanation of symbols]

1 Speech synthesizer 2 voice recognition device 3 Text comparison section 11 Language Processing Department 12 language dictionary 13 Phoneme processing unit 14 Phonological dictionary 15 Parameter generator 16 Parameter storage 17 Parameter selection section 21 Speech recognition processing unit 22 Similarity determination unit

─────────────────────────────────────────────────── ─── Continued Front Page (51) Int.Cl. ⁷ Identification Code FI Theme Coat (Reference) G10L 15/22 G10L 3/00 537C

Claims (12)

[Claims] 1. A text is input to a voice synthesizing means, the text is subjected to a voice synthesizing process using a parameter necessary for the voice synthesizing, and is output as a voice signal. And the text input to the speech synthesizing means are compared, the parameter is set to a certain value based on the comparison result, the learning parameter is set as the learning parameter, and the speech signal obtained by speech synthesis by the learning parameter is obtained. Is output as a speech synthesis result. 2. The process of setting the parameter to a certain value based on the comparison result and using it as a learning parameter until the text as the voice recognition result matches the text input to the voice synthesizing means. 2. The speech synthesis method according to claim 1, which is a process of changing the parameter and using a parameter when both match as a learning parameter. 3. The speech synthesis method according to claim 1, wherein the learning parameter is stored. 4. When a plurality of candidates are present as the parameters when the text is input to the voice synthesizing means and the text is subjected to the voice synthesizing process using the parameters necessary for the voice synthesizing, the plurality of candidates are A certain parameter is selected, voice synthesis is performed using the selected parameter, the voice synthesis result is voice-recognized, and the similarity between the voice recognition result and the text input to the voice synthesis means is determined, Based on the similarity determination result, one of the parameters of the plurality of candidates is selected, the selected parameter is used as a learning parameter, and a speech signal obtained by speech synthesis with the learning parameter is used as a speech synthesis result. A method for synthesizing speech, which is characterized by outputting as. 5. The process of selecting one of the parameters of the plurality of candidates based on the similarity determination result and using the selected parameter as a learning parameter, the similarity becomes equal to or more than a predetermined value. 5. The speech synthesis method according to claim 4, further comprising the step of sequentially selecting the candidate parameters and using the parameter having the similarity of a predetermined value or more as a learning parameter. 6. The speech synthesis method according to claim 4, wherein the learning parameter is stored. 7. A voice synthesizing means for inputting a text, performing a voice synthesizing process of the text using a parameter necessary for performing a voice synthesizing, and outputting as a voice signal, and a voice signal output from the voice synthesizing means. Voice recognition means for recognizing voice and outputting the voice recognition result as text, and text comparison means for comparing the text as the recognition result by the voice recognition means with the text input to the voice synthesizing means, The speech synthesis means sets the parameter to a certain value based on the result of comparison between the text as the recognition result output from the text comparison means and the text input to the speech synthesis means, and sets it as a learning parameter. , And outputs a voice signal obtained by voice synthesis based on the learning parameter as a voice synthesis result. Speech synthesizer. 8. The process of setting the parameter to a certain value based on the comparison result and using it as a learning parameter, the text as the recognition result output from the text comparison means is input to the voice synthesis means. 8. The speech synthesizer according to claim 7, wherein the parameter is changed until the matched text matches, and the parameter when the two match is used as a learning parameter. 9. The voice synthesizing apparatus according to claim 7, wherein the voice synthesizing means is provided with a parameter storage means, and the learning parameter is stored in the parameter storage means. 10. When a text is input to a voice synthesizing means and the text is subjected to a voice synthesizing process using a parameter required for the voice synthesizing, when a plurality of candidates exist as the parameter, among the plurality of candidates, A voice synthesizing unit that selects a certain parameter, performs a voice synthesizing process using the selected parameter, and outputs as a voice signal, recognizes the voice signal output from the voice synthesizing unit, and recognizes the recognition result and the voice. And a voice recognition means capable of outputting a similarity determination result by determining the similarity to the text input to the synthesizing means, wherein the voice synthesizing means is based on the similarity determination result from the voice recognizing means. , One of the plurality of candidates is selected, the selected parameter is used as a learning parameter, and the speech is synthesized by the learning parameter. Speech synthesis apparatus and outputs as a speech synthesis result an audio signal. 11. The process of selecting one of the parameters of the plurality of candidates based on the similarity determination result and using the selected parameter as a learning parameter is such that the similarity is equal to or more than a predetermined value. 11. The voice synthesizing apparatus according to claim 10, wherein the process is performed by sequentially selecting the candidate parameters and using the parameter having a similarity equal to or more than a predetermined value as a learning parameter. 12. The voice synthesizing apparatus according to claim 10, wherein the voice synthesizing unit is provided with a parameter storage unit, and the learning parameter is stored in the parameter storage unit.