Tree-based unit selection for English speech synthesis

Wern Jun Wang, W. N. Campbell, Naoto Iwahashi, Yoshinori Sagisaka

研究成果: Conference contribution

10 被引用数 (Scopus)

抄録

In concatenative speech synthesis for English, scarcity of speech data for many contexts is a serious problem. In this paper, we propose a new unit selection scheme using a decision-tree-based clustering method that combines acoustic and linguistic knowledge with statistical modeling. This approach not only allows us to find a trainable and consistent set of generalized allophonic models but also to achieve some local optimality with respect to the limited training data. To evaluate the validity of this algorithm, regression tree generation has been carried out for both vowels and consonants from 200 phonetically balanced sentences read by a female speaker. Experimental results show that regression trees offer a promising solution for the data scarcity problem.

本文言語English
ホスト出版物のタイトルSpeech Processing
出版社Publ by IEEE
ページII-191-II-194
ISBN(印刷版)0780309464
出版ステータスPublished - 1993 1 1
外部発表はい
イベント1993 IEEE International Conference on Acoustics, Speech and Signal Processing - Minneapolis, MN, USA
継続期間: 1993 4 271993 4 30

出版物シリーズ

名前Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing
2
ISSN(印刷版)0736-7791

Other

Other1993 IEEE International Conference on Acoustics, Speech and Signal Processing
CityMinneapolis, MN, USA
Period93/4/2793/4/30

ASJC Scopus subject areas

  • ソフトウェア
  • 信号処理
  • 電子工学および電気工学

フィンガープリント

「Tree-based unit selection for English speech synthesis」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