Blind Source Separation with Distributed Microphone Pairs Using Permutation Correction by Intra-Pair TDOA Clustering

In this paper, we present a novel framework of distributed microphone array for blind source separation (BSS), where stereo microphones or proximately-placed microphone pairs are distributed. Unlike distributing all microphones individually, the time difference of arrival (TDOA) in the paired channels can be robustly estimated without suffering spatial aliasing. Based on it, sound sources are separated by the frequency-domain independent component analysis (ICA) with the permutation correction by clustering the intra-pair TDOAs. The experimental results in real reverberant environment are also shown.