Blind source separation based on time-domain optimization of a frequency-domain independence criterion

Authors

Tiemin Mei, Dalian University of Technology, ChinaFollow
Jiangtao Xi, University of WollongongFollow
Fuliang Yin, Dalian University of Technology
A. Mertins, University of WollongongFollow
Jose F. Chicharo, University of WollongongFollow

RIS ID

17510

Publication Details

Mei, T., Xi, J., Yin, F., Mertins, A. Chicharo, J. F. (2006). Blind source separation based on time-domain optimization of a frequency-domain independence criterion. IEEE Transactions on Audio, Speech and Language Processing, 14 (6), 2075-2085.

Abstract

A new technique for the blind separation of convolutive mixtures is proposed in this paper. Inspired by the works of Amari, Sabala , and Rahbar, we firstly start from the application of Kullback-Leibler divergence in frequency domain, and then we integrate Kullback-Leibler divergence over the whole frequency range of interest to yield a new objective function which turns out to be time-domain variable dependent. In other words, the objective function is derived in frequency domain which can be optimized with respect to time domain variables. The proposed technique has the advantages of frequency domain approaches and is suitable for very long mixing channels, but does not suffer from the local permutation problem as the separation is achieved in time-domain.