Speech Recognition Under the Unstationary Noise Based on the Noise Markov Model and Spectral-Subtraction

Tetsunori Kobayashi*, Ryuji Mine, Katsuhiko Shirai

*この研究の対応する著者

研究成果: Paper査読

3 被引用数 (Scopus)

抄録

In this paper, mechanisms to recognize speech in time varying noise are proposed. In these methods, the noise source and the speech source are modeled independently. The probabilities that these two models emit observed data sequence are calculated. We tested two methods. The first one uses HMMs to model both of noise and speech. The second one uses a normal Morkov model for noise representation. Adopting normal Markov model, the noise model itself become rather complex, however, the dynamical features such as delta cepstrum can be easily and precisely considered. Using these methods, 100 word recognition tests in car noise environment are performed. As the results, the performances are improved by 23 % and 26 % using the first and the second method, respectively, as compared with normal spectral subtraction.

本文言語English
ページ833-836
ページ数4
出版ステータスPublished - 1993
イベント3rd European Conference on Speech Communication and Technology, EUROSPEECH 1993 - Berlin, Germany
継続期間: 1993 9月 221993 9月 25

Conference

Conference3rd European Conference on Speech Communication and Technology, EUROSPEECH 1993
国/地域Germany
CityBerlin
Period93/9/2293/9/25

ASJC Scopus subject areas

  • ソフトウェア
  • 言語学および言語
  • コンピュータ サイエンスの応用
  • 通信

フィンガープリント

「Speech Recognition Under the Unstationary Noise Based on the Noise Markov Model and Spectral-Subtraction」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