Convolutive Blind Source Separation with Wiener post-filtering for robust Speech Recognition

LEANDRO DI PERSIA; DIEGO MILONE; MASUZO YANAGIDA

Mendoza

Congreso; Argentine Symposium of Technology (AST2006); 2006

SADIO

Blind source separation for convolutive mixtures of soundsources is a complex task, mainly because the mixing filters are long and non-minimum phase. One approach to solve this problem is frequency domain blind source separation, in which the separation is calculated for each frequency bin in the  time-frequency domain. Although there are several methods for this task, separation quality is degraded by many factors. This paper presents a method for separation in time-frequency domain, that combines the advantages of other two separation methodsand uses a time-frequency Wiener filter as post-processing to increase separation quality. The algorithm has been evaluated over a database of Spanish speech recorded in a reverberant room using two active sound sources and two microphones. Speech recognition results show an increment in recognition rate of the separated speech in the order of 70% from the noisy case.