Stereo-based feature enhancement using dictionary learning

Shinji Watanabe, John R. Hershey

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

This paper proposes stereo-based speech feature enhancement using dictionary learning. Instead of posterior values obtained by a Gaussian mixture as in other methods, we use sparse weight vectors and their variants as an alternative noisy speech feature representation. This paper also provides an efficient algorithm that can be applied to large-scale speech processing. We show the effectiveness of the proposed approach by using a middle vocabulary noisy speech recognition task based on WSJ, which was provided by the 2nd CHiME Speech Separation and Recognition Challenge.

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7073-7077
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

「Stereo-based feature enhancement using dictionary learning」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