Communicative Speech Synthesis with XIMERA: A First Step


NAIST \| Library	Advanced Search	Japanese \| English

Please use this identifier to cite or link to this item: http://hdl.handle.net/10061/8270

Title:	Communicative Speech Synthesis with XIMERA: A First Step
Authors:	Sinsuke Sakai Jinfu Ni Ranniery Maia Keiichi Tokuda Minoru Tsuzaki Tomoki Toda Hisashi Kawai Satoshi Nakamura
Issue Date:	Aug-2007
Start page:	28
End page:	33
Abstract:	This paper presents a corpus-based approach to communicative speech synthesis. We chose "good news" style and "bad news" style for our initial attempt to synthesize speech that has appropriate expressiveness desired in human-human or human-machine dialog. We utilized 10-hour "neutral" style speech corpus as well as smaller corpora with good news and bad news styles, each consisting of two to three hours of speech from the same speaker. We trained target HMM models with each style and synthesized speech with unit databases containing speech with the relevant style as well as neutral speech. From the listening tests, we found out that intended communicative styles were comprehended by listeners and that considerably high mean opinion score on naturalness was achieved with rather small, style-specific corpora.
Description:	SSW6: 6th ISCA Speech Synthesis Workshop, August 22-24, 2007, Bonn, Germany.
URI:	http://hdl.handle.net/10061/8270
Text Version:	Publisher
Appears in Collections:	情報科学研究科 / Graduate School of Information Science

Files in This Item:

File	Description	Size	Format
SSW_2007_28.pdf		353.37 kB	Adobe PDF	View/Open
presentation.pdf		670.72 kB	Adobe PDF	View/Open