Does dereverberation help multichannel blind source separation? A study case

Abstract :

Multichannel blind source separation performances rapidly degrade when the mixtures are highly reverberated. In fact, blind source separation algorithms usually focus on the separation task without dealing with the dereverberation problem. Some recent studies attempted to reduce the reverberation by introducing a dereverberation module before or after the blind source separation but only limited success was obtained in improving the separation performance in highly reverberant rooms. In this article, we conduct a number of experiments combining state of the art spectral enhancement-based dereverberation and source separation algorithms showing that, in this particular case, speech enhancement does not improve the performance of blind source separation. Index Terms— Blind source separation, speech

Document type :
Conference papers
Complete list of metadatas
Contributor : Telecomparis Hal <>
Submitted on : Friday, September 13, 2019 - 4:07:37 PM
Last modification on : Thursday, October 17, 2019 - 12:37:02 PM


  • HAL Id : hal-02286737, version 1



Nicolás López, Mounira Maazaoui, Yves Grenier, Gael Richard, Ivan Bourmeyster. Does dereverberation help multichannel blind source separation? A study case. European Signal Processing Conference (EUSIPCO), Sep 2013, Marrakech, Morocco. ⟨hal-02286737⟩



Record views