PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Two-microphone Separation of Speech Mixtures
Michael Syskind Pedersen, DeLiang Wang, Jan Larsen and Ulrik Kjems
IEEE Transactions on neural Networks 2006.

Abstract

Separation of speech mixtures, often referred to as the ocktail party problem, has been studied for decades. In many source separation tasks, the separation method is limited by the assumption of at least as many sensors as sources. Further, many methods require that the number of signals within the recorded mixtures be known in advance. In many real-world applications these limitations are too restrictive. We propose a novel method for underdetermined blind source separation using an instantaneous mixing model which assumes closely spaced microphones. Two source separation techniques have been combined, independent component analysis (ICA) and binary time-frequency masking. By estimating binary masks from the outputs of an ICA algorithm, it is possible in an iterative way to extract basis speech signals from a convolutive mixture. The basis signals are afterwards improved by grouping similar signals. Using two microphones we can separate in principle an arbitrary number of mixed speech signals. We show separation results for mixtures with as many as seven speech signals under anechoic conditions. We also show that the proposed method is applicable to segregate speech signals under reverberant conditions, and we compare our proposed method to another state-of-the-art algorithm. The number of source signals is not assumed to be known in advance and it is possible to maintain the extracted signals as stereo signals.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Speech
Theory & Algorithms
ID Code:2781
Deposited By:Michael Pedersen
Deposited On:22 November 2006