ALTERNATIVE STRUCTURES AND POWER SPECTRUM CRITERIA FOR BLIND SEGMENTATION AND SEPARATION OF CONVOLUTIVE SPEECH MIXTURES
Benoit Albouy, Yannick Deville · 2003
This paper deals with the blind separation of convolutively mixed speech sources. The proposed methods take advantage of the a priori knowledge that speech signals contain silences. They con-sist in first detecting silence phases in these source signals and then identifying each filter of the considered separating systems in such a phase. The criteria used in both stages of these approaches are based on the power (cross)-spectra of the observations: their time-segmented coherence function is first used to detect silence phases and the filters to be identified are then expressed as the ra-tios of observation power (cross)-spectra. This general approach is applied to various separating systems, depending i) whether the considered structures are symmetrical, asymmetrical, or asymmet-rical with a complementary part, and ii) whether they include or not a post-processing stage for filtering the extracted sources. The performance of all these approaches and of two methods from the literature is investigated by means of experimental tests performed with speech sources mixed by means of real acoustical in-car trans-fer functions. This shows that the proposed approaches yield an interesting performance/complexity trade-off as compared to pre-viously reported methods. 1.