VOICE SYNTHESIS APPARATUS BASED ON SINGLE-MODEL VOICE RECOGNITION SYNTHESIS, VOICE SYNTHESIS METHOD AND VOICE SYNTHESIS PROGRAM

Title:

VOICE SYNTHESIS APPARATUS BASED ON SINGLE-MODEL VOICE RECOGNITION SYNTHESIS, VOICE SYNTHESIS METHOD AND VOICE SYNTHESIS PROGRAM

Document Type and Number:

WIPO Patent Application WO/2010/104040

Kind Code:

A1

Abstract:

Disclosed are a voice synthesis apparatus, voice synthesis method and voice synthesis program capable of implementing voice synthesis of a specified individual with high quality using few items of learned voice data. The voice synthesis apparatus learns a transition model (225) of articulatory movement stored for each of fixed voice units such as phonemes, from an unspecified large number of speakers. The voice synthesis apparatus is provided with means (230) for converting to voice synthesis parameters that carry vocal tract shape information whereby a series of articulatory features is adapted to individuals and an optimum voice unit series is obtained at the same time by comparing this model with the input voice. In addition, the voice synthesis apparatus obtains high-quality synthesised voice for a specified individual by registering sound source code in a state transition model of articulatory movement using closed loop learning employing a drive sound source codebook.

More Like This:

JP5498439	Phoneme Labeling Data Phoneme Duration Length Conversion Method and Its Devices and Programs
JP4025355	Speech synthesizer and speech synthesizer

Inventors:

NITTA TSUNEO (JP)

Application Number:

PCT/JP2010/053802

Publication Date:

September 16, 2010

Filing Date:

March 08, 2010

Export Citation:

Click for automatic bibliography generation Help

Assignee:

NAT UNIV CORP TOYOHASHI UNIV T (JP)
NITTA TSUNEO (JP)

International Classes:

G10L13/06; G10L13/00; G10L13/10

Foreign References:

JP2004012584A	2004-01-15
JP2003271182A	2003-09-25
JP2002351791A	2002-12-06
JP2000066694A	2000-03-03

Other References:

KEIICHI TOKUDA: "Speech Syntehsis Based on Hidden Markov Models", IEICE TECHNICAL REPORT, vol. 99, no. 255, 5 August 1999 (1999-08-05), pages 47 - 54
JUN HIROI ET AL.: "Very Low Bit Rate Speech Coding Based on HMMs", IEICE TECHNICAL REPORT, vol. 98, no. 264, 11 September 1998 (1998-09-11), pages 39 - 44

Attorney, Agent or Firm:

IKAWA Hirofumi et al. (JP)
Hirofumi Ikawa (JP)

Download PDF:

View/Download PDF PDF Help

Previous Patent: GLASS SUBSTRATE AND METHOD FOR MANUFACTURING SAME

Next Patent: THIN FILM SOLAR CELL AND PRODUCTION METHOD THEREOF