Microphone-location dependent mask estimation for BSS using spatially distributed asynchronous microphones

Distributed microphone array (DMA) processing has recently been attracting a lot of attention as a promising alternative to conventional microphone arrays with co-located elements. To perform efficient blind source separation (BSS) using spatially distributed microphones, we have recently proposed an approach for estimating microphone-dependent mask, equivalently microphone-dependent source activity, and performing BSS based on such information. Our method was proposed based on the fact that, in DMA scenarios, the source activities observable at any given microphone may be significantly different from those of others when the microphones are spatially distributed to a great degree, and the level of each signal at each microphone varies significantly. In this paper, we revisit the formulation of the proposed method, and investigate its performance in the presence of drift error, i.e., the sampling frequency mismatch between different microphones. To make the proposed method robust to drift error, we introduce different parameter initialization schemes and analyze their effect on the overall performance of the proposed method.