Perceptually enhanced blind single-channel music source separation by Non-negative Matrix Factorization

Kirbiz S., Gunsel B.

DIGITAL SIGNAL PROCESSING, vol.23, no.2, pp.646-658, 2013 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 23 Issue: 2
  • Publication Date: 2013
  • Doi Number: 10.1016/j.dsp.2012.10.001
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.646-658
  • Istanbul Technical University Affiliated: Yes


We propose a new approach that improves perceptual quality of the separated sources in blind single-channel musical source separation. It uses the advantages of subspace learning based on Non-negative Matrix Factorization (NMF) in which the bases represent the notes. The cost function is formulated in the form of weighted beta-divergence by adopting the PEAQ auditory model defined in ITU-R BS.1387 into the source separation. The proposed perceptually weighted factorization scheme is integrated into the Non-negative Matrix Factor 2-D Deconvolution (NMF2D) and Clustered Non-negative Matrix Factorization (CNMF) to overcome the source clustering problem encountered in under-determined source separation. It is shown that the introduced perceptually weighted NMF schemes, named as PW-NMF2D and PW-CNMF, efficiently learn the bases that enable us to apply a simple resynthesis of the musical sources based on the temporal model stored in the encoding matrix. Source separation performance has been reported on musical mixtures where 1-2 dB improvement is achieved in terms of SDR, SIR and SAR compared to the state-of-the-art methods. Performance has also been evaluated by perceptual measures resulting an improvement of 2-5 in OPS, TPS, IPS and APS values. (C) 2012 Elsevier Inc. All rights reserved.