Blind Source Separation Based on a Beamformer Array and Time Frequency Binary Masking

Jan Cermak, Shoko Araki, Hiroshi Sawada, Shoji Makino

Abstract: This paper deals with a new technique for blind source separation (BSS) from convolutive mixtures. We present a three-stage separation system employing time-frequency binary masking, beamforming and a non-linear post processing technique. The experiments show that this system outperforms conventional time-frequency binary masking (TFBM) in both (over-)determined and underdetermined cases. Moreover it removes the musical noise and reduces interference in time-frequency slots extracted by TFBM.