A Sparseness - Mixing Matrix Estimation (SMME) solving the underdetermined BSS for convolutive mixtures

Audrey Blin*, Shoko Araki, Shoji Makino

*この研究の対応する著者

研究成果: Conference article査読

6 被引用数 (Scopus)

抄録

We propose a method for blindly separating real environment speech signals with as less distortion as possible in the special case where speech signals outnumber sensors. Our idea consists in combining sparseness with the use of an estimated mixing matrix. First, we use a geometrical approach to perform a preliminary separation and to detect when only one source is active. This information is then used to estimate the mixing matrix. Then we remove one source from the observations and separate the residual signals with the inverse of the estimated mixing matrix. Experimental results in a real environment (TR=130ms and 200ms) show that our proposed method, which we call Sparseness - Mixing Matrix Estimation (SMME). provides separated signals of better quality than those extracted by only using the sparseness property of the speech signal.

本文言語English
ページ(範囲)IV-85-IV-88
ジャーナルICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
4
出版ステータスPublished - 2004
外部発表はい
イベントProceedings - IEEE International Conference on Acoustics, Speech, and Signal Processing - Montreal, Que, Canada
継続期間: 2004 5月 172004 5月 21

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

「A Sparseness - Mixing Matrix Estimation (SMME) solving the underdetermined BSS for convolutive mixtures」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