Rule based speech synthesis method and apparatus

• US 7,765,103 B2
• Filed: 06/09/2004
• Issued: 07/27/2010
• Est. Priority Date: 06/13/2003
• Status: Expired due to Fees

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: Yamazaki, Nobuhide
• Primary Examiner(s): Vo; Huyen X.
• Application Number:
  US10/864,130
• Publication Number:
  US 20050119889A1
• Time in Patent Office: 2,239 Days
• Field of Search: 704/260, 704/258, 704/261, 704/266, 704/270, 704/231, 704/268, 704/270.1, 704/257, 704/235, 704/259, 704/7
• US Class Current: 704/259
• CPC Class Codes: G10L 13/07 Concatenation rules

Abstract

A rule based speech synthesis apparatus by which concatenation distortion may be less than a preset value without dependency on utterance, wherein a parameter correction unit reads out a target parameter for a vowel from a target parameter storage, responsive to the phoneme at a leading end and at a trailing end of a speech element and acoustic feature parameters output from a speech element selector, and accordingly corrects the acoustic feature parameters of the speech element. The parameter correction unit corrects the parameters, so that the parameters ahead and behind the speech element are equal to the target parameter for the vowel of the corresponding phoneme, and outputs the corrected parameters.

Claims

1. A rule based speech synthesis apparatus comprising

speech element set storage means for storing a plurality of phoneme strings, each having a vowel phoneme on a boundary thereof, as a speech element, along with feature parameters, as a speech element set;

speech element selection means for reading out acoustic feature parameters of a corresponding speech element from said speech element set storage means, based on an input phoneme string;

target parameter storage means having stored therein representative acoustic feature parameters from one vowel to another;

parameter correction means for reading out a target parameter comprising acoustic parameters from one vowel to another for a vowel from said target parameter storage means in response to the acoustic feature parameter of the speech element output from said speech element selection means and for correcting the acoustic feature parameter of said speech element based on said target parameters, the acoustic feature parameter being corrected according to at least one predetermined equation wherein the corrected acoustic feature parameter is a function of at least a first target value for a parameter at a leading edge of said speech element and a second target value for a parameter at a trailing edge of said speech element, the corrected acoustic feature having a value equal to said first target value at said leading edge of said speech element and a value equal to said second target value at said trailing edge of said speech element;

time-series data generating means for concatenating plural acoustic feature parameters output from said parameter correction means to generate time series data of the acoustic feature parameters; and

speech synthesizing means for uttering and outputting speech signals of the synthesized speech corresponding to the input phoneme strings in accordance with time-series data of the acoustic feature parameters, corresponding to the input phoneme strings, generated by said time-series data generating means.

2. The rule based speech synthesis apparatus according to claim 1 wherein said parameter correction means corrects the acoustic feature parameters of the speech element from a leading end to a leading end to a trailing end of the speech element as a subject of correction.

3. The rule based speech synthesis apparatus according to claim 1 wherein said parameter correction means determines a temporal boundary of a leading end and a trailing end of the speech element as said plurality of phoneme strings as a fixed length.

4. The rule based speech synthesis apparatus according to claim 1 wherein said parameter correction means determines a temporal boundary of a leading end and a trailing end of the speech element as said phoneme strings in accordance with a boundary of the vowel and the consonant.

5. A rule based speech synthesis method of using a processor to perform steps comprising

a speech element selecting step of reading out an acoustic feature parameter corresponding to a speech element, based on input phoneme strings, from a speech element set storage storing a plurality of phoneme strings, each having a vowel phoneme on the boundary, as a speech element, along with feature parameters, as a speech element set;

a parameter correction step of reading out a target parameter comprising acoustic parameters from one vowel to another for a vowel, in response to the acoustic feature parameters of the speech element output in said speech element selecting step from the target parameter storage having stored therein representative acoustic feature parameters from one vowel to another for correcting the acoustic feature parameters of said speech element based on said target parameter, the acoustic feature parameters being corrected according to at least one predetermined equation wherein the corrected acoustic feature parameters are a function of at least a first target value for a parameter at a leading edge of said speech element and a second target value for a parameter at a trailing edge of said speech element, the corrected acoustic feature having a value equal to said first target value at said leading edge of said speech element and a value equal to said second target value at said trailing edge of said speech element;

a time series data generating step of generating time series data of the acoustic feature parameters by concatenating the acoustic feature parameters output from said parameter correction step; and

a speech synthesis step of uttering and outputting a speech signal of the synthesized speech, corresponding to said input of phoneme strings, in accordance with the acoustic feature parameters, corresponding to said input phoneme strings, generated in said time series data generating step.

6. A rule based speech synthesis apparatus comprising

speech element set storage means for storing a plurality of phoneme strings, each having a vowel phoneme on a boundary thereof, as a speech element, along with feature parameters of each speech element, as a speech element set;

speech element selection means for reading out acoustic feature parameters of a corresponding speech element from said speech element set storage means based on an input phoneme string;

target parameter storage means having stored therein a plurality of acoustic feature parameters from one vowel to another;

parameter correction means for selecting a specified acoustic feature parameter in response to an acoustic feature parameter of said speech element selection means, from target parameters comprising acoustic parameters from one vowel to another stored in said target parameter storage means and for correcting the acoustic feature parameter of the speech element responsive to the selected specified acoustic feature parameter, the acoustic feature parameter being corrected according to at least one predetermined equation wherein the corrected acoustic feature parameter is a function of at least a first target value for a parameter at a leading edge of said speech element and a second target value for a parameter at a trailing edge of said speech element, the corrected acoustic feature having a value equal to said first target value at said leading edge of said speech element and a value equal to said second target value at said trailing edge of said speech element;

time-series data generating means for concatenating plural acoustic feature parameters output from said parameter correction means to generate time series data of the acoustic feature parameters; and

speech synthesizing means for uttering and outputting speech signals of synthesized speech corresponding to the input phoneme strings, based on time-series data of the acoustic feature parameters, corresponding to the input phoneme strings, generated by said time-series data generating means.

7. The rule based speech synthesis apparatus according to claim 6 wherein said parameter correction means selects a target parameter having a smallest error between a parameter at a trailing end of the speech element output from said speech element set storage means and a plurality of acoustic feature parameters stored in said target parameter storage means, as a specified acoustic feature parameter.

8. The rule based speech synthesis apparatus according to claim 6 wherein said parameter correction means selects a target parameter from the acoustic feature parameters stored in said target parameter storage means based on an error between a parameter at a trailing end of the speech element output from said speech element set storage means and the acoustic feature parameters store in said target parameter storage means, as a specified acoustic feature parameter.

9. The rule based speech synthesis apparatus according to claim 8 wherein said parameter correction means selects such an acoustic feature parameter having a smallest value of a sum of an error between a parameter at a trailing end of the speech element and said plural acoustic feature parameters and an error between a parameter at a leading end of the speech element and said plural acoustic feature parameters, as a specified acoustic feature parameter.

10. The rule based speech synthesis apparatus according to claim 8 wherein said parameter correction means selects such an acoustic feature parameter from said plural acoustic feature parameters which has an error between the parameter at a trailing end of said speech element and the respective acoustic feature parameters or an acoustic feature parameter from said plural acoustic feature parameters that has an error between the parameter at a leading end of said speech element and the respective acoustic feature parameters, whichever has the smaller error.

11. A rule based speech synthesis method of using a processor to perform steps comprising

a speech element set selecting step of reading out and outputting an acoustic feature parameter of a corresponding speech element, based on input phoneme strings, from a speech element set storage adapted for storing plural phoneme strings each having a vowel phoneme on the boundary, as a speech element, as a set of the speech element with the acoustic feature parameter;

a parameter correcting step of selecting, from target parameters comprising acoustic parameters from one vowel to another stored in a target parameter storage, a specified acoustic feature parameter, responsive to the acoustic feature parameter of the speech element output from the speech element selecting step, and for correcting the acoustic feature parameter of the speech element based on the selected specified acoustic feature parameter, the acoustic feature parameter being corrected according to at least one predetermined equation wherein the corrected acoustic feature parameter is a function of at least a first target value for a parameter at a leading edge of said speech element and a second target value for a parameter at a trailing edge of said speech element, the corrected acoustic feature having a value equal to said first target value at said leading edge of said speech element and a value equal to said second target value at said trailing edge of said speech element;

a time-series data generating step of concatenating plural acoustic feature parameters output from said parameter correction step to generate time series data of the acoustic feature parameters; and

speech synthesizing means for uttering and outputting speech signals of the synthesized speech, corresponding to the input phoneme strings, in accordance with time-series data of acoustic feature parameters, corresponding to the input phoneme strings, generated by said time-series data generating step.

12. A rule based speech synthesis apparatus comprising

speech element set storage means for storing a plurality of phoneme strings, each having a consonant phoneme on a boundary thereof, as a speech element, along with feature parameters, as a speech element set;

speech element selection means for reading out acoustic feature parameters of a corresponding speech element, from said speech element set storage means, based on input phoneme strings;

target parameter storage means having stored therein a representative acoustic feature parameter from one consonant to another;

parameter correction means for reading out a target parameter for a consonant from said target parameter storage means having stored therein target parameters comprising acoustic parameters from one consonant to another, responsive to the acoustic feature parameters of the speech element, output from said speech element selection means, and for correcting the acoustic feature parameters of said speech element based on said target parameters, the acoustic feature parameters being corrected according to at least one predetermined equation wherein the corrected acoustic feature parameters are a function of at least a first target value for a parameter at a leading edge of said speech element and a second target value for a parameter at a trailing edge of said speech element, the corrected acoustic feature having a value equal to said first target value at said leading edge of said speech element and a value equal to said second target value at said trailing edge of said speech element;

time-series data generating means for concatenating plural acoustic feature parameters output from said parameter correction means to generate time series data of the acoustic feature parameters; and

speech synthesizing means for uttering and outputting speech signals of synthesized speech corresponding to the input phoneme strings in accordance with time-series data of the acoustic feature parameters, corresponding to the input phoneme strings, generated by said time-series data generating means.

13. A rule based speech synthesis method of using a processor to perform steps comprising

a speech element selecting step of reading out acoustic feature parameters of a corresponding speech element, based on an input phoneme string from a speech element set storage adapted for storing a plurality of phoneme strings, each having a consonant phoneme on the boundary, as a speech element, along with feature parameters, as a speech element set;

a parameter correction step of reading out a target parameter for a consonant, responsive to the acoustic feature parameters of the speech element output in said speech element selecting step from the target parameter storage having stored therein target parameters comprising acoustic parameters from one consonant to another, and for correcting the acoustic feature parameters of said speech element based on said target parameter, the acoustic feature parameters being corrected according to at least one predetermined equation wherein the corrected acoustic feature parameters are a function of at least a first target value for a parameter at a leading edge of said speech element and a second target value for a parameter at a trailing edge of said speech element, the corrected acoustic feature having a value equal to said first target value at said leading edge of said speech element and a value equal to said second target value at said trailing edge of said speech element;

a time series data generating step of generating time series data of the acoustic feature parameters by concatenating the acoustic feature parameters output from said parameter correction step; and

a speech synthesis step of uttering and outputting a speech signal of synthesized speech, corresponding to said input phoneme strings, accordance with the time series data of the acoustic feature parameters, corresponding to said input phoneme strings, generated in said time series data generating step.