A sparseness-mixing matrix estimation (SMME) solving the underdetermined BSS for convolutive mixtures

Abstract

We propose a method for blindly separating real environment speech signals with as little 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… (More)
DOI: 10.1109/ICASSP.2004.1326769

Topics

7 Figures and Tables

Slides referencing similar topics