A Novel Blind Source Separation Framework Towards Maximum Signal-To-Interference Ratio

TL;DR

This paper introduces MVICA, a new blind source separation framework that optimizes for maximum SIR, improving separation performance and robustness over existing methods, supported by neural network implementation and experimental validation.

Contribution

The paper develops MVICA, a novel BSS framework that maximizes SIR and relaxes independence assumptions, with a neural network-based implementation for practical use.

Findings

MVICA outperforms state-of-the-art BSS algorithms in SIR and signal quality.

MVICA improves automatic speech recognition accuracy.

Experimental results demonstrate robustness across various conditions.

Abstract

This letter proposes a new blind source separation (BSS) framework termed minimum variance independent component analysis (MVICA), which can potentially achieve the maximum output signal-to-interference ratio (SIR) while also allowing more flexibility in real implementations. The statistical independence assumption has been the foundation of the most dominant BSS techniques in recent decades. However, this assumption does not always hold true and the accurate probabilistic modeling of source is inherently difficult. To overcome these limitations and improve the separation performance, the MVICA framework is rigorously derived by optimizing the design of these independence-based BSS algorithms with the maximum SIR criterion. A deep neural network-supported implementation of MVICA is subsequently described. Experimental results under various conditions show the superiority of MVICA over the state-of-the-art BSS algorithms, in terms of not only SIR but also signal-to-distortion ratio and automatic speech recognition rate.