SPEECH EXTRACTION BASED UPON A COMBINED SUBBAND INDEPENDENT COMPONENT ANALYSIS AND NEURAL MEMORY

Tetsuya Hoya, Allan K. Barros, Tomasz M Rutkowski, Andrzej Cichocki

Abstract:

This paper presents a novel approach for speech
extraction by a combined subband independent com
ponent analysis and neural memory. In the approach,
probabilistic neural networks followed by the subband
independent component analysis processing units are
used for the neural memory to identify firstly the speaker
and then compensate for the `side-effects', i.e., the scal
ing and the permutation disorder, both of which are
particularly problematic for subband blind extraction.
Simulation study shows that the combined scheme can
effectively extract the speech signal of interest from
the instantaneous / delayed mixtures, in comparison
with the conventional subband/fullband approaches