A RobustICA Based Algorithm for Blind Separation of Convolutive Mixtures

TL;DR

This paper introduces a robust frequency domain ICA-based algorithm for blind source separation of convolutive speech mixtures, especially effective in highly reverberant environments with limited observation data.

Contribution

It presents a novel regularized RICA algorithm that improves separation performance in reverberant conditions and compares different permutation solving techniques.

Findings

Outperforms RR ICA and IVA in reverberant environments

Effective with short observation signals

Parameter impacts on separation performance analyzed

Abstract

We propose a frequency domain method based on robust independent component analysis (RICA) to address the multichannel Blind Source Separation (BSS) problem of convolutive speech mixtures in highly reverberant environments. We impose regularization processes to tackle the ill-conditioning problem of the covariance matrix and to mitigate the performance degradation in the frequency domain. We apply an algorithm to separate the source signals in adverse conditions, i.e. high reverberation conditions when short observation signals are available. Furthermore, we study the impact of several parameters on the performance of separation, e.g. overlapping ratio and window type of the frequency domain method. We also compare different techniques to solve the frequency-domain permutation ambiguity. Through simulations and real world experiments, we verify the superiority of the presented convolutive algorithm among other BSS algorithms, including recursive regularized ICA (RR ICA), independent vector analysis (IVA).