Convergence analysis for a class of source separation methods

Abstract

Blind Source Separation (BSS) is a topic of interest in different fields of information processing with a large span of applications, e.g., in communications, pattern recognition, brain activity monitoring and audio processing. This article reviews some convergence analysis results for parallel BSS algorithms that are used for the simultaneous extraction of sources. The emphasis will be on two major BSS schemes, namely, Indepenent Component Analysis and Bounded Component Analysis. The article underlines the major convergence results regarding these two branches and their connections.