An event-driven f(o) weighting for prosody control in a large corpus-based TTS system
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Byeon, HJ | ko |
| dc.contributor.author | Oh, Yung-Hwan | ko |
| dc.date.accessioned | 2010-03-22T09:05:52Z | - |
| dc.date.available | 2010-03-22T09:05:52Z | - |
| dc.date.created | 2012-02-06 | - |
| dc.date.created | 2012-02-06 | - |
| dc.date.issued | 2004-02 | - |
| dc.identifier.citation | IEEE SIGNAL PROCESSING LETTERS, v.11, pp.262 - 265 | - |
| dc.identifier.issn | 1070-9908 | - |
| dc.identifier.uri | http://hdl.handle.net/10203/17283 | - |
| dc.description.abstract | This letter presents event-driven weighting methods concentrating on f(0) for prosody control in a large corpus-based text-to-speech (TTS) system. We determine the f(0) weighting factor for a given target using its linguistic features by automatically using classification and regression trees (CART). The target predicted as perceptually important is weighted more than others. This results in more natural synthetic speech from a prosodic viewpoint. | - |
| dc.language | English | - |
| dc.language.iso | en_US | en |
| dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
| dc.title | An event-driven f(o) weighting for prosody control in a large corpus-based TTS system | - |
| dc.type | Article | - |
| dc.identifier.wosid | 000188369800036 | - |
| dc.identifier.scopusid | 2-s2.0-0442279656 | - |
| dc.type.rims | ART | - |
| dc.citation.volume | 11 | - |
| dc.citation.beginningpage | 262 | - |
| dc.citation.endingpage | 265 | - |
| dc.citation.publicationname | IEEE SIGNAL PROCESSING LETTERS | - |
| dc.identifier.doi | 10.1109/LSP.2003.821684 | - |
| dc.contributor.localauthor | Oh, Yung-Hwan | - |
| dc.contributor.nonIdAuthor | Byeon, HJ | - |
| dc.type.journalArticle | Article | - |
| dc.subject.keywordAuthor | CART | - |
| dc.subject.keywordAuthor | event-driven f(o) weighting | - |
| dc.subject.keywordAuthor | large corpus-based TTS system | - |
- Appears in Collection
- CS-Journal Papers(저널논문)
- Files in This Item
- 000188369800036.pdf(121.45 kB)Download
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.