DSpace Repository

Communicative Speech Synthesis with XIMERA: A First Step

Show simple item record

dc.contributor.author Sinsuke Sakai ja
dc.contributor.author Jinfu Ni ja
dc.contributor.author Ranniery Maia ja
dc.contributor.author Keiichi Tokuda ja
dc.contributor.author Minoru Tsuzaki ja
dc.contributor.author Tomoki Toda ja
dc.contributor.author Hisashi Kawai ja
dc.contributor.author Satoshi Nakamura ja
dc.date.accessioned 2012-08-22T07:59:01Z
dc.date.available 2012-08-22T07:59:01Z
dc.date.issued 2007-08 ja
dc.identifier.uri http://hdl.handle.net/10061/8270
dc.description SSW6: 6th ISCA Speech Synthesis Workshop, August 22-24, 2007, Bonn, Germany. ja
dc.description.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. ja
dc.language.iso en ja
dc.title Communicative Speech Synthesis with XIMERA: A First Step ja
dc.type.nii Conference Paper ja
dc.textversion Publisher ja
dc.identifier.spage 28 ja
dc.identifier.epage 33 ja
dc.identifier.NAIST-ID 73296626
dc.identifier.NAIST-ID 73292716

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace

Advanced Search


My Account