Presentation 2013-01-30
F0 Contour Generation Using Rich Context Models in HMM-Based Speech Synthesis
Shinnosuke TAKAMICHI, Tomoki TODA, Yoshinori SHIGA, Sakriani SAKTI, Graham NEUBIG, Satoshi NAKAMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In the traditional HMM-based speech synthesis, generated speech parameters tend to be excessively over-smoothed. To alleviate this problem, we have proposed a spectral parameter generation method with rich context models and have showed its effectiveness. In this paper, we propose a F0 contour generation method with the rich context models, which are successfully applied to Multi-Space probability Distribution HMM (MSD-HMM) for modeling F0 contour. Experimental evaluations demonstrate that the proposed method yields significant improvements in the quality of synthetic speech.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) F0 contour generation / MSD-HMM / rich context models / parameter generation method
Paper # SP2012-104
Date of Issue

Conference Information
Committee SP
Conference Date 2013/1/23(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 Speech (SP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) F0 Contour Generation Using Rich Context Models in HMM-Based Speech Synthesis
Sub Title (in English)
Keyword(1) F0 contour generation
Keyword(2) MSD-HMM
Keyword(3) rich context models
Keyword(4) parameter generation method
1st Author's Name Shinnosuke TAKAMICHI
1st Author's Affiliation Nara Institute of Science and Technology()
2nd Author's Name Tomoki TODA
2nd Author's Affiliation Nara Institute of Science and Technology
3rd Author's Name Yoshinori SHIGA
3rd Author's Affiliation National Institute of Information and Communications Technology
4th Author's Name Sakriani SAKTI
4th Author's Affiliation Nara Institute of Science and Technology
5th Author's Name Graham NEUBIG
5th Author's Affiliation Nara Institute of Science and Technology
6th Author's Name Satoshi NAKAMURA
6th Author's Affiliation Nara Institute of Science and Technology
Date 2013-01-30
Paper # SP2012-104
Volume (vol) vol.112
Number (no) 422
Page pp.pp.-
#Pages 6
Date of Issue