A style control technique for speech synthesis using multiple regression HSMM

Takashi Nose, Junichi Yamagishi, Takao Kobayashi

研究成果: Conference contribution

13 被引用数 (Scopus)

抄録

This paper presents a technique for controlling intuitively the degree or intensity of speaking styles and emotional expressions of synthetic speech. The conventional style control technique based on multiple regression HMM (MRHMM) has a problem that it is difficult to control phone duration of synthetic speech because HMM has no explicit parameter which models phone duration appropriately. To overcome this problem, we use multiple regression hidden semi-Markov model (MRHSMM) which has explicit state duration distributions to control phone duration. We show that the duration control is important for style control of synthetic speech from the results of subjective tests. We also compare the proposed technique with another control technique based on model interpolation.

本文言語English
ホスト出版物のタイトルINTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP
出版社International Speech Communication Association
ページ1324-1327
ページ数4
3
ISBN(印刷版)9781604234497
出版ステータスPublished - 2006 1 1
外部発表はい
イベントINTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP - Pittsburgh, PA, United States
継続期間: 2006 9 172006 9 21

Other

OtherINTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP
国/地域United States
CityPittsburgh, PA
Period06/9/1706/9/21

ASJC Scopus subject areas

  • コンピュータ サイエンス(全般)

フィンガープリント

「A style control technique for speech synthesis using multiple regression HSMM」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル