SPEECH SYNTHESIZER, SPEECH SYNTHESIS METHOD, AND SPEECH SYNTHESIS PROGRAM

• US 20120316881A1
• Filed: 03/23/2011
• Published: 12/13/2012
• Est. Priority Date: 03/25/2010
• Status: Abandoned Application

• Current Assignee: NEC Corporation
• Original Assignee: NEC Corporation
• Inventors: Kato, Masanori
• Application Number:
  US13/576,406
• Publication Number:
  US 20120316881A1
• Time in Patent Office: Days
• US Class Current: 704/260
• CPC Class Codes: G10L 13/06 Elementary speech units used in speech synthesisers; Concatenation rules
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination

Abstract

A normalized spectrum storage unit 204 prestores normalized spectra calculated based on a random number series. A voiced sound generating unit 201 generates voiced sound waveforms based on a plurality of segments of voiced sounds corresponding to an inputted text and the normalized spectra stored in the normalized spectrum storage unit 204. An unvoiced sound generating unit 202 generates unvoiced sound waveforms based on a plurality of segments of unvoiced sounds corresponding to the inputted text. A synthesized speech generating unit 203 generates a synthesized speech based on the voiced sound waveforms generated by the voiced sound generating unit 201 and the unvoiced sound waveforms generated by the unvoiced sound generating unit 202.

Claims

1-10. -10. (canceled)

11. A speech synthesizer which generates a synthesized speech of an inputted text, comprising:

a voiced sound generating unit which includes a normalized spectrum storage unit prestoring one or more normalized spectra calculated based on a random number series and generates voiced sound waveforms based on a plurality of segments of voiced sounds corresponding to the text and the normalized spectra stored in the normalized spectrum storage unit;

an unvoiced sound generating unit which generates unvoiced sound waveforms based on a plurality of segments of unvoiced sounds corresponding to the text; and

a synthesized speech generating unit which generates the synthesized speech based on the voiced sound waveforms generated by the voiced sound generating unit and the unvoiced sound waveforms generated by the unvoiced sound generating unit.

12. The speech synthesizer according to claim 11, wherein the voiced sound generating unit generates a plurality of pitch waveforms based on the normalized spectra stored in the normalized spectrum storage unit and amplitude spectra as segments of voiced sounds corresponding to the text and generates the voiced sound waveform based on the generated pitch waveforms.

13. The speech synthesizer according to claim 11, wherein the voiced sound generating unit generates time-domain waveforms based on the normalized spectra stored in the normalized spectrum storage unit, generates an excited signal based on the generated time-domain waveforms and prosody corresponding to the inputted text, and generates the voiced sound waveform based on the generated excited signal.

14. The speech synthesizer according to claim 11, wherein one or more normalized spectra calculated by using a group delay based on a random number series is prestored in the normalized spectrum storage unit.

15. The speech synthesizer according to claim 11, wherein:

the normalized spectrum storage unit prestores two or more normalized spectra, and

the voiced sound generating unit generates each voiced sound waveform by using a normalized spectrum different from that used for generating the previous voiced sound waveform.

16. The speech synthesizer according to claim 11, wherein the number of normalized spectra stored in the normalized spectrum storage unit is within a range from 2 to a million.

17. A speech synthesis method for generating a synthesized speech of an inputted text, comprising:

generating voiced sound waveforms based on a plurality of segments of voiced sounds corresponding to the text and one or more normalized spectra stored in a normalized spectrum storage unit prestoring the normalized spectra calculated based on a random number series;

generating unvoiced sound waveforms based on a plurality of segments of unvoiced sounds corresponding to the text; and

generating the synthesized speech based on the generated voiced sound waveforms and the generated unvoiced sound waveforms.

18. The speech synthesis method according to claim 17, wherein:

generating a plurality of pitch waveforms based on the normalized spectra stored in the normalized spectrum storage unit and amplitude spectra as segments of voiced sounds corresponding to the text, and

generating the voiced sound waveform based on the generated pitch waveforms.

19. A computer readable information recording medium storing a speech synthesis program, when executed,

generating voiced sound waveforms based on a plurality of segments of voiced sounds corresponding to the text and one or more normalized spectra stored in a normalized spectrum storage unit prestoring the normalized spectra calculated based on a random number series;

generating unvoiced sound waveforms based on a plurality of segments of unvoiced sounds corresponding to the text; and

generating the synthesized speech based on generated voiced sound waveforms and generated unvoiced sound waveforms.

20. The computer readable information recording medium according to claim 19, when executed, generating a plurality of pitch waveforms based on the normalized spectra stored in the normalized spectrum storage unit and amplitude spectra as segments of voiced sounds corresponding to the text and generates the voiced sound waveform based on the generated pitch waveforms.