Effectiveness of discriminative training and feature transformation for reverberated and noisy speech

Yuuki Tachioka, Shinji Watanabe, John R. Hershey

研究成果: Conference contribution

13 被引用数 (Scopus)

抄録

Automatic speech recognition in the presence of non-stationary interference and reverberation remains a challenging problem. The 2nd 'CHiME' Speech Separation and Recognition Challenge introduces a new and difficult task with time-varying reverberation and non-stationary interference including natural background speech, home noises, or music. This paper establishes baselines using state-of-the-art ASR techniques such as discriminative training and various feature transformation on the middle-vocabulary sub-task of this challenge. In addition, we propose an augmented discriminative feature transformation that introduces arbitrary features to a discriminative feature transformation. We present experimental results showing that discriminative training of model parameters and feature transforms is highly effective for this task, and that the augmented feature transformation provides some preliminary benefits. The training code will be released as an advanced ASR baseline.

本文言語English
ホスト出版物のタイトル2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings
ページ6935-6939
ページ数5
DOI
出版ステータスPublished - 2013 10月 18
外部発表はい
イベント2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Vancouver, BC, Canada
継続期間: 2013 5月 262013 5月 31

出版物シリーズ

名前ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN(印刷版)1520-6149

Conference

Conference2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013
国/地域Canada
CityVancouver, BC
Period13/5/2613/5/31

ASJC Scopus subject areas

  • ソフトウェア
  • 信号処理
  • 電子工学および電気工学

フィンガープリント

「Effectiveness of discriminative training and feature transformation for reverberated and noisy 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