A new time-frequency approach for underdetermined convolutive blind speech separation

Mariem Bouafif; Zied Lachiri

ICASSP 2016accepted0 citations

A new time-frequency approach for underdetermined convolutive blind speech separation

Abstract

In this paper, we present a new Time-Frequency approach for recovering sources' contribution to two convolutive mixtures. The separation task is performed on two steps: Each mixture is clustered into Voiced/Unvoiced frames, and then the predominant source in each time frequency bin is identified through a specific weight function which is based on sources' excitation characteristics extraction. We investigate the performance of the proposed approach in the un-derdetermined context using objective quality measures. Results for separating three and four speech sources in a live recorded mixture show the superiority of the proposed method in rejecting artifacts over existing convolutive separation techniques.

BibTeX

@inproceedings{icassp2016_anewtimefrequenc,
  title = {A new time-frequency approach for underdetermined convolutive blind speech separation},
  author = {Mariem Bouafif and Zied Lachiri},
  booktitle = {ICASSP 2016},
  year = {2016}
}