Discriminative training of acoustic models for system combination

Yuuki Tachioka, Shinji Watanabe

研究成果: Conference article

4 引用 (Scopus)

抜粋

In discriminative training methods, the objective function is designed to improve the performance of automatic speech recognition with reference to correct labels using a single system. On the other hand, system combination methods, which output refined hypotheses by a majority voting scheme, need to build multiple systems that generate complementary hypotheses. This paper aims to unify the both requirements within a discriminative training framework based on the mutual information criterion. That is, we construct complementary models by optimizing the proposed objective function, which yields to minimize the mutual information with base systems' hypotheses, while maximize that with correct labels, at the same time. We also analyze that this scheme corresponds to weight the training data of a complementary system by considering correct and error tendencies in the base systems, which has close relationship with boosting methods. In addition, the proposed method can practically construct complementary systems by simply extending a lattice-based parameter update algorithm in discriminative training, and can adjust the degree of how much the complementary system outputs are different from base system ones. The experiments on highly noisy speech recognition ('The 2nd CHiME challenge') show the effectiveness of the proposed method, compared with a conventional system combination approach.

元の言語English
ページ(範囲)2355-2359
ページ数5
ジャーナルProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
出版物ステータスPublished - 2013 1 1
外部発表Yes
イベント14th Annual Conference of the International Speech Communication Association, INTERSPEECH 2013 - Lyon, France
継続期間: 2013 8 252013 8 29

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modelling and Simulation

フィンガープリント Discriminative training of acoustic models for system combination' の研究トピックを掘り下げます。これらはともに一意のフィンガープリントを構成します。

  • これを引用