Markov model based noise modeling and its application to noisy speech recognition using dynamical features of speech

Tetsunori Kobayashi, Ryuji Mine, Katsuhiko Shirai

研究成果: Conference article査読

3 被引用数 (Scopus)

抄録

In this paper, some algorithms to recognize speech in time varying noise are proposed. In the proposed methods, Spectral subtraction and Markov model based noise models are successfully utilized in the framework of spectral decomposition of noisy speech. Firstly, we considered the problem of the mis-subtraction noise which is caused in the subtraction based decomposition procedure. Then, the precise use of dynamical feature of speech such as delta cepstrum is discussed. Using the methods proposed here, recognition performance are improved more than 60 % compared to no compensation method.

本文言語English
論文番号389719
ページ(範囲)II57-II60
ジャーナルICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
2
DOI
出版ステータスPublished - 1994
イベントProceedings of the 1994 IEEE International Conference on Acoustics, Speech and Signal Processing. Part 2 (of 6) - Adelaide, Aust
継続期間: 1994 4 191994 4 22

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

フィンガープリント 「Markov model based noise modeling and its application to noisy speech recognition using dynamical features of speech」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