A Unifying View on Blind Source Separation of Convolutive Mixtures based on Independent Component Analysis

TL;DR

This paper provides a comprehensive framework unifying various ICA-based methods for convolutive blind source separation, clarifying their relationships and differences in audio signal processing.

Contribution

It offers an in-depth analysis of the common components and distinctions among FD-ICA, IVA, and TRINICON algorithms, establishing a unified theoretical framework.

Findings

Clarifies the relationships between ICA, FD-ICA, IVA, and TRINICON methods.

Provides a common framework for understanding these algorithms.

Enhances theoretical understanding of convolutive BSS techniques.

Abstract

In many daily-life scenarios, acoustic sources recorded in an enclosure can only be observed with other interfering sources. Hence, convolutive Blind Source Separation (BSS) is a central problem in audio signal processing. Methods based on Independent Component Analysis (ICA) are especially important in this field as they require only few and weak assumptions and allow for blindness regarding the original source signals and the acoustic propagation path. Most of the currently used algorithms belong to one of the following three families: Frequency Domain ICA (FD-ICA), Independent Vector Analysis (IVA), and TRIple-N Independent component analysis for CONvolutive mixtures (TRINICON). While the relation between ICA, FD-ICA and IVA becomes apparent due to their construction, the relation to TRINICON is not well established yet. This paper fills this gap by providing an in-depth treatment of the common building blocks of these algorithms and their differences, and thus provides a common framework for all considered algorithms.