Underdetermined blind speech separation with directivity pattern based continuous mask and ICA

Shoko Araki, Shoji Makino, Hiroshi Sawada, Ryo Mukai

研究成果: Conference contribution

4 被引用数 (Scopus)

抄録

We propose a method for separating speech signals when sources outnumber the sensors. In this paper we mainly concentrate on the case of three sources and two sensors. Some existing methods employ binary masks to extract the signals, and therefore, the extracted signals contain loud musical noise. To overcome this problem, we propose the utilization of a directivity pattern based continuous mask, which removes a single source from the observations, and independent component analysis (ICA) to separate the remaining mixtures. Experimental results show that our proposed method can separate signals with little distortion even in a real reverberant environment of T R =130 ms.

本文言語English
ホスト出版物のタイトル2004 12th European Signal Processing Conference, EUSIPCO 2004
出版社European Signal Processing Conference, EUSIPCO
ページ1991-1994
ページ数4
ISBN(電子版)9783200001657
出版ステータスPublished - 2015 4 3
外部発表はい
イベント12th European Signal Processing Conference, EUSIPCO 2004 - Vienna, Austria
継続期間: 2004 9 62004 9 10

出版物シリーズ

名前European Signal Processing Conference
06-10-September-2004
ISSN(印刷版)2219-5491

Conference

Conference12th European Signal Processing Conference, EUSIPCO 2004
国/地域Austria
CityVienna
Period04/9/604/9/10

ASJC Scopus subject areas

  • 信号処理
  • 電子工学および電気工学

フィンガープリント

「Underdetermined blind speech separation with directivity pattern based continuous mask and ICA」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