Data-Driven Source Separation Based on Simplex Analysis

TL;DR

This paper introduces a novel data-driven method for blind source separation of multichannel audio using spectral decomposition and simplex analysis, effectively identifying and extracting individual speakers even in reverberant environments.

Contribution

The paper presents a new approach combining spectral decomposition and convex geometry to recover the number of speakers and separate their signals from multichannel audio.

Findings

High separation accuracy demonstrated across different reverberation conditions

Effective identification of speaker-specific time frames using simplex geometry

Robust estimation of mixing channels through convex analysis

Abstract

Blind source separation (BSS) is addressed, using a novel data-driven approach, based on a well-established probabilistic model. The proposed method is specifically designed for separation of multichannel audio mixtures. The algorithm relies on spectral decomposition of the correlation matrix between different time frames. The probabilistic model implies that the column space of the correlation matrix is spanned by the probabilities of the various speakers across time. The number of speakers is recovered by the eigenvalue decay, and the eigenvectors form a simplex of the speakers' probabilities. Time frames dominated by each of the speakers are identified exploiting convex geometry tools on the recovered simplex. The mixing acoustic channels are estimated utilizing the identified sets of frames, and a linear umixing is performed to extract the individual speakers. The derived simplexes are visually demonstrated for mixtures of 2, 3 and 4 speakers. We also conduct a comprehensive experimental study, showing high separation capabilities in various reverberation conditions.