A regularized discriminative training method of acoustic models derived by minimum relative entropy discrimination

Yotaro Kubo, Shinji Watanabe, Atsushi Nakamura, Tetsunori Kobayashi

研究成果: Paper

5 引用 (Scopus)

抜粋

We present a realization method of the principle of minimum relative entropy discrimination (MRED) in order to derive a regularized discriminative training method. MRED is advantageous since it provides a Bayesian interpretations of the conventional discriminative training methods and regularization techniques. In order to realize MRED for speech recognition, we proposed an approximation method of MRED that strictly preserves the constraints used in MRED. Further, in order to practically perform MRED, an optimization method based on convex optimization and its solver based on the cutting plane algorithm are also proposed. The proposed methods were evaluated on continuous phoneme recognition tasks. We confirmed that the MRED-based training system outperformed conventional discriminative training methods in the experiments.

元の言語English
ページ2954-2957
ページ数4
出版物ステータスPublished - 2010 12 1
イベント11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010 - Makuhari, Chiba, Japan
継続期間: 2010 9 262010 9 30

Conference

Conference11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010
Japan
Makuhari, Chiba
期間10/9/2610/9/30

    フィンガープリント

ASJC Scopus subject areas

  • Language and Linguistics
  • Speech and Hearing

これを引用

Kubo, Y., Watanabe, S., Nakamura, A., & Kobayashi, T. (2010). A regularized discriminative training method of acoustic models derived by minimum relative entropy discrimination. 2954-2957. 論文発表場所 11th Annual Conference of the International Speech Communication Association: Spoken Language Processing for All, INTERSPEECH 2010, Makuhari, Chiba, Japan.