A comparative study on sparsity penalties for NMF-based speech separation: Beyond LP-norms

Cyril Joder, Felix Weninger, David Virette, Bjorn Schuller

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

20 Scopus citations

Abstract

In this work, we study the usefulness of several types of sparsity penalties in the task of speech separation using supervised and semi-supervised Nonnegative Matrix Factorization (NMF). We compare different criteria from the literature to two novel penalty functions based on Wiener Entropy, in a large-scale evaluation on spontaneous speech overlaid by realistic domestic noise, as well as music and stationary environmental noise corpora. The results show that enforcing the sparsity constraint in the separation phase does not improve the perceptual quality. In the learning phase however, it yields a better estimation of the base spectra, especially in the case of supervised NMF, where the proposed criteria delivered the best results.

Original languageEnglish
Title of host publication2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings
Pages858-862
Number of pages5
DOIs
StatePublished - 18 Oct 2013
Event2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Vancouver, BC, Canada
Duration: 26 May 201331 May 2013

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)1520-6149

Conference

Conference2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013
Country/TerritoryCanada
CityVancouver, BC
Period26/05/1331/05/13

Keywords

  • Source separation
  • noise cancellation
  • single-channel speech enhancement

Fingerprint

Dive into the research topics of 'A comparative study on sparsity penalties for NMF-based speech separation: Beyond LP-norms'. Together they form a unique fingerprint.

Cite this