English

Generalized Minimal Distortion Principle for Blind Source Separation

Audio and Speech Processing 2020-09-14 v1 Sound Signal Processing

Abstract

We revisit the source image estimation problem from blind source separation (BSS). We generalize the traditional minimum distortion principle to maximum likelihood estimation with a model for the residual spectrograms. Because residual spectrograms typically contain other sources, we propose to use a mixed-norm model that lets us finely tune sparsity in time and frequency. We propose to carry out the minimization of the mixed-norm via majorization-minimization optimization, leading to an iteratively reweighted least-squares algorithm. The algorithm balances well efficiency and ease of implementation. We assess the performance of the proposed method as applied to two well-known determined BSS and one joint BSS-dereverberation algorithms. We find out that it is possible to tune the parameters to improve separation by up to 2 dB, with no increase in distortion, and at little computational cost. The method thus provides a cheap and easy way to boost the performance of blind source separation.

Keywords

Cite

@article{arxiv.2009.05288,
  title  = {Generalized Minimal Distortion Principle for Blind Source Separation},
  author = {Robin Scheibler},
  journal= {arXiv preprint arXiv:2009.05288},
  year   = {2020}
}

Comments

5 pages, 1 figure, 2 tables, Accepted at INTERSPEECH 2020

R2 v1 2026-06-23T18:27:59.886Z