Presentation 2001/10/1
Investigation of State Duration Model based on Gamma distribution for HMM-based Speech Synthesis
Yoshinobu ISHIMATSU, Keiichi TOKUDA, Takashi MASUKO, Takao KOBAYASHI, Tadashi KITAMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We propose a new approach to state duration modeling based on Gamma distribution for HMM-based speech synthesis. We have proposed the text-to-speech synthesis, in which state durations are modeled by using Gaussian distribution, and shown its effectiveness. The Gamma distribution is defined for positive real numbers, and has the distribution form which fits well for state duration modeling. For this reason, we expected that the Gamma distribution enables us to model state durations with higher accuracy. The experimental results show that the proposed duration modeling technique yields the speech quality comparable to or higher with few duration models than the conventional technique.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Gamma distribution / state duration model / context clustering / speech synthesis
Paper # SP2001-81,WIT2001-35
Date of Issue

Conference Information
Committee WIT
Conference Date 2001/10/1(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Well-being Information Technology(WIT)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Investigation of State Duration Model based on Gamma distribution for HMM-based Speech Synthesis
Sub Title (in English)
Keyword(1) Gamma distribution
Keyword(2) state duration model
Keyword(3) context clustering
Keyword(4) speech synthesis
1st Author's Name Yoshinobu ISHIMATSU
1st Author's Affiliation Department of Computer Science, Nagoya Inst.of Tech.()
2nd Author's Name Keiichi TOKUDA
2nd Author's Affiliation Department of Computer Science, Nagoya Inst.of Tech.
3rd Author's Name Takashi MASUKO
3rd Author's Affiliation Interdisciplinary Graduate School of Science and Engineering, Tokyo Inst.of Tech.
4th Author's Name Takao KOBAYASHI
4th Author's Affiliation Interdisciplinary Graduate School of Science and Engineering, Tokyo Inst.of Tech.
5th Author's Name Tadashi KITAMURA
5th Author's Affiliation Department of Computer Science, Nagoya Inst.of Tech.
Date 2001/10/1
Paper # SP2001-81,WIT2001-35
Volume (vol) vol.101
Number (no) 353
Page pp.pp.-
#Pages 6
Date of Issue