ENHANCEMENT OF A SPEECH SIGNAL EMBEDDED IN NOISY ENVIRONMENT USING TWO MICROPHONES
Allan Kardec Barros 1;5 , Hideki Kawahara 2 , Andrzej Cichocki 3
Email: akbarros@ieee.org
In this work we develop a system for enhancement of
a speech signal with the highest energy from a linear
convolutive mixture of independent sound sources (in
terferences) recorded by two microphone signals. In
this system we use the concept of independent compo
nent analysis (ICA) together with auditory filter banks,
pitch tracking, adaptive band pass filters and masking.
Preliminary computer simulations experiments confirm
the validity of the proposed algorithm.