Dividing the distributions of HMM and linear interpolation in speech recognition

Kiyoshi Asai, Satoru Hayamizu, Ken'ichi Handa

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

In this paper, we present an explicit criterion for deciding whether to divide the HMM-based phone model into more precise(for example, context dependent) models, or not. We also discuss the cases when linear interpolations of these models are used, and present an explicit solution of the interpolation weight λ. These criteria are obtained by evaluating the estimation errors of the distributions of these models. We show that the estimation errors should be evaluated by the projected covariance matrices of the estimation errors of the logarithm of the probabilities.

本文言語English
ホスト出版物のタイトルICASSP 1992 - 1992 International Conference on Acoustics, Speech, and Signal Processing
出版社Institute of Electrical and Electronics Engineers Inc.
ページ29-32
ページ数4
ISBN(電子版)0780305329
DOI
出版ステータスPublished - 1992
外部発表はい
イベント1992 International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1992 - San Francisco, United States
継続期間: 1992 3 231992 3 26

出版物シリーズ

名前ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
1
ISSN(印刷版)1520-6149

Other

Other1992 International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1992
国/地域United States
CitySan Francisco
Period92/3/2392/3/26

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

「Dividing the distributions of HMM and linear interpolation in speech recognition」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