A generalized discriminative training framework for system combination

Yuuki Tachioka, Shinji Watanabe, Jonathan Le Roux, John R. Hershey

研究成果

5 被引用数 (Scopus)

抄録

This paper proposes a generalized discriminative training framework for system combination, which encompasses acoustic modeling (Gaussian mixture models and deep neural networks) and discriminative feature transformation. To improve the performance by combining base systems with complementary systems, complementary systems should have reasonably good performance while tending to have different outputs compared with the base system. Although it is difficult to balance these two somewhat opposite targets in conventional heuristic combination approaches, our framework provides a new objective function that enables to adjust the balance within a sequential discriminative training criterion. We also describe how the proposed method relates to boosting methods. Experiments on highly noisy middle vocabulary speech recognition task (2nd CHiME challenge track 2) and LVCSR task (Corpus of Spontaneous Japanese) show the effectiveness of the proposed method, compared with a conventional system combination approach.

本文言語English
ホスト出版物のタイトル2013 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2013 - Proceedings
ページ43-48
ページ数6
DOI
出版ステータスPublished - 2013
外部発表はい
イベント2013 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2013 - Olomouc, Czech Republic
継続期間: 2013 12 82013 12 13

出版物シリーズ

名前2013 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2013 - Proceedings

Other

Other2013 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2013
国/地域Czech Republic
CityOlomouc
Period13/12/813/12/13

ASJC Scopus subject areas

  • 言語聴覚療法

フィンガープリント

「A generalized discriminative training framework for system combination」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