DeepAI AI Chat
Log In Sign Up

Data-Driven Source Separation Based on Simplex Analysis

by   Bracha Laufer-Goldshtein, et al.
Bar-Ilan University

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.


page 4

page 8

page 10


Multi-Decoder DPRNN: High Accuracy Source Counting and Separation

We propose an end-to-end trainable approach to single-channel speech sep...

Blind Source Separation over Space

We propose a new estimation method for the spatial blind source separati...

Hierarchical Probabilistic Model for Blind Source Separation via Legendre Transformation

We present a novel blind source separation (BSS) method, called informat...

End-to-End Multi-speaker ASR with Independent Vector Analysis

We develop an end-to-end system for multi-channel, multi-speaker automat...

Multi-scenario deep learning for multi-speaker source separation

Research in deep learning for multi-speaker source separation has receiv...

Time Series Source Separation using Dynamic Mode Decomposition

The dynamic mode decomposition (DMD) extracted dynamic modes are the non...

Double Coupled Canonical Polyadic Decomposition for Joint Blind Source Separation

Joint blind source separation (J-BSS) is an emerging data-driven techniq...