Presentation	2013-12-20 Toward Speech Synthesis with Diverse Voices and Styles : Approaches and Issues Takao KOBAYASHI,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	Recently, hidden Markov model-based(HMM-based) speech synthesis has been widely studied in the text-to-speech (TTS) synthesis research area. The author has been developing HMM-based speech synthesis systems toward the realization of synthetic speech with diverse expressiveness, including voice characteristics, emotions, speaking styles, and spontaneity, for over 10 years. This paper presents an overview of various approaches to expressive speech synthesis proposed by the author and also describes future work.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Text-to-speech synthesis / HMM-based speech synthesis / expressive speech synthesis / average voice model / style control
Paper #	SP2013-93
Date of Issue

Conference Information
Committee	SP
Conference Date	2013/12/12(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)	Toward Speech Synthesis with Diverse Voices and Styles : Approaches and Issues
Sub Title (in English)
Keyword(1)	Text-to-speech synthesis
Keyword(2)	HMM-based speech synthesis
Keyword(3)	expressive speech synthesis
Keyword(4)	average voice model
Keyword(5)	style control
1st Author's Name	Takao KOBAYASHI
1st Author's Affiliation	Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology()
Date	2013-12-20
Paper #	SP2013-93
Volume (vol)	vol.113
Number (no)	366
Page	pp.pp.-
#Pages	4
Date of Issue