Initialization method for speech separation algorithms that work in the time-frequency domain

Abstract

This article addresses the problem of the unsupervised separa tion of speech signals in realistic scenarios. An initialization procedure is proposed for independent component analysis (ICA) algorithms that work in the time-frequency domain and require the prewhitening of the observations. It is shown that the proposed method drastically reduces the permuted solu tions in that domain and helps to reduce the execution time of the algorithms. Simulations confirm these advantages for several ICA instantaneous algo rithms and the effectiveness of the proposed technique in emulated reverber ant environments.