Blind Source Separation of Convolutive Mixtures of Speech in Frequency Domain

This paper overviews a total solution for frequencydomain blind source separation (BSS) of convolutive mixtures of audio signals, especially speech. Frequency-domain BSS performs independent component analysis (ICA) in each frequency bin, and this is more efficient than time-domain BSS. We describe a sophisticated total solution for frequency-domain BSS, including permutation, scaling, circularity, and complex activation function solutions. Experimental results of 2× 2, 3× 3, 4 × 4, 6 × 8, and 2 × 2 (moving sources), (#sources × #microphones) in a room are promising. key words: blind source separation, convolutive mixtures, independent component analysis, frequency-domain BSS, microphone array, adaptive beamformer