Generalized Minimal Distortion Principle for Blind Source Separation
This provides a cheap and easy way to boost performance for blind source separation, though it is incremental as it builds on existing methods.
The authors tackled the problem of source image estimation in blind source separation by generalizing the minimum distortion principle to maximum likelihood estimation with a mixed-norm model for residual spectrograms, resulting in up to 2 dB improvement in separation with no increase in distortion and low computational cost.
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.