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 引用 (Scopus)

抜粋

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.

元の言語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
出版物ステータスPublished - 2013 10 18
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 262013 5 31

出版物シリーズ

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

Conference

Conference2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013
Canada
Vancouver, BC
期間13/5/2613/5/31

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

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

    Tachioka, Y., Watanabe, S., & Hershey, J. R. (2013). Effectiveness of discriminative training and feature transformation for reverberated and noisy speech. : 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings (pp. 6935-6939). [6639006] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2013.6639006