Blind Source Separation of Acoustic Signals Based on Multistage Independent Component Analysis

Summer Meeting of Acoustical Society of Korea, August 2002.We propose a new algorithm for blind source separation (BSS), in which frequency-domain ICA (TDICA) are combined to achieve a superior source-separation performance under reverberant conditions. Generally speaking, conventional TDICA fails to separate source signals under heavily reverberant conditions because of hte low convergence in the iterative learning of hte inverse of the mixing system. On the other hand, the separation performance of conventional FDICA also degrades significantly because the independence assumption of narrow-band signals collapses when the number of subbands increases. In the proposed method, the separated signals of FDICA are regarded as the input signals for TDICA, and we can remove the residual crosstalk components of FDICA by using TDICA. The experimental results obtained under the reverberant condition reveal that the separation performance of hte proposed method is superior to that of conventional ICA-based BSS methods