A structured nonnegative matrix factorization for source separation

Clement Laroche, Matthieu Kowalski, Helene Papadopoulos, Gael Richard

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

Abstract

In this paper, we propose a new unconstrained nonnegative matrix factorization method designed to utilize the multilayer structure of audio signals to improve the quality of the source separation. The tonal layer is sparse in frequency and temporally stable, while the transient layer is composed of short term broadband sounds. Our method has a part well suited for tonal extraction which decomposes the signals in sparse orthogonal components, while the transient part is represented by a regular nonnegative matrix factorization decomposition. Experiments on synthetic and real music data in a source separation context show that such decomposition is suitable for audio signal. Compared with three state-of-the-art harmonic/percussive decomposition algorithms, the proposed method shows competitive performances.

Original languageEnglish
Title of host publication2015 23rd European Signal Processing Conference, EUSIPCO 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2033-2037
Number of pages5
ISBN (Electronic)9780992862633
DOIs
Publication statusPublished - 22 Dec 2015
Externally publishedYes
Event23rd European Signal Processing Conference, EUSIPCO 2015 - Nice, France
Duration: 31 Aug 20154 Sept 2015

Publication series

Name2015 23rd European Signal Processing Conference, EUSIPCO 2015

Conference

Conference23rd European Signal Processing Conference, EUSIPCO 2015
Country/TerritoryFrance
CityNice
Period31/08/154/09/15

Keywords

  • audio source separation
  • harmonic/percussive decomposition
  • nonnegative matrix factorization
  • projective nonnegative matrix factorization

Fingerprint

Dive into the research topics of 'A structured nonnegative matrix factorization for source separation'. Together they form a unique fingerprint.

Cite this