A fixed point solution for convolved audio source separation

Nikolaos Mitianoudis, Mike Davies

To appear at Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA01), Mohonk Mountain Resort, NY, 21-24 October 2001


We examine the problem of blind audio source separation using Independent Component Analysis (ICA). In order to separate audio sources recorded in a real recording environment, we need to model the mixing process as convolutional. Many methods have been introduced for separating convolved mixtures, the most successful of which require working in the frequency domain. This paper proposes a fixed-point algorithm for performing frequency domain ICA on speech and audio sources, aiming for faster convergence. The algorithm was tested on a series of speech and audio samples with quite promising results. Moreover, we are examining a method to increase the stability and enhance the performance of previous maximum likelihood frequency domain ICA algorithms.

Server START Conference Manager
Update Time 5 Jul 2001 at 16:08:04
Maintainer malcolm@ieee.org.
Start Conference Manager
Conference Systems