Blind separation of convolved sources based on information maximization

Abstract

Blind separation of independent sources from thieir corrvolutive mixtures is a problem in many real world multi-sensor applications. In this paper we present a solution to this problem lbased on the information maximization principle, which was recently proposed by Bell and Sejnowski for the case of blind separation of instantaneous mixtures. We present a feedback network architecture capable of coping with convolutive mixtures, and we derive the adaiptation equations for the adaptive filters in the network by maximizing the information transferred through the network. :Examples using speech signals are presented to illustrate the algorithm.

A dynamic algorithm for blind separation of convolutive sound mixtures

“…An interesting line of future work will be concerned with various strategies to reduce computational costs. (2) and (3), as proposed in [19]. Fig.…”

Gradient Adaptive Paraunitary Filter Banks for Spatio-Temporal Subspace Analysis and Multichannel Blind Deconvolution

“…Solutions to the above task are useful for separating digital communications signals in an unknown multiuser environment [49,50] as well as separating acoustic signals from multisensor recordings in reverberant room environments [51][52][53]. We now develop algorithms for multichannel blind deconvolution for prewhitened signal mixtures.…”

A clustering approach for the blind separation of multiple finite alphabet sequences from a single linear mixture

“…Second order statistics can be also used provided that the source signals are colored [5]. These methods have found applications in array signal processing [27], speech separation [36], medical signal processing [21], industrial fault detection [33], feature extraction for image and speech data [23,2,3], etc. For a thorough discussion of ICA, BSS and related topics see [18,7].…”