Skip to main navigation Skip to search Skip to main content

A tempering approach for Itakura-Saito non-negative matrix factorization. With application to music transcription

  • CNRS LTCI

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

27 Citations (Scopus)

Abstract

In this paper we are interested in non-negative matrix factorization (NMF) with the Itakura-Saito (IS) divergence. Previous work has demonstrated the relevance of this cost function for the decomposition of audio power spectrograms. This is in particular due to its scale invariance, which makes it more robust to the wide dynamics of audio, a property which is not shared by other popular costs such as the Euclidean distance or the generalized Kulback-Leibler (KL) divergence. However, while the latter two cost functions are convex, the IS divergence is not, which makes it more prone to convergence to irrelevant local minima, as observed empirically. Thus, the aim of this paper is to propose a tempering scheme that favors convergence of IS-NMF to global minima. Our algorithm is based on NMF with the beta-divergence, where the shape parameter beta acts as a temperature parameter. Results on both synthetical and music data (in a transcription context) show the relevance of our approach.

Original languageEnglish
Title of host publication2009 IEEE International Conference on Acoustics, Speech, and Signal Processing - Proceedings, ICASSP 2009
Pages1545-1548
Number of pages4
DOIs
Publication statusPublished - 23 Sept 2009
Externally publishedYes
Event2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009 - Taipei, Taiwan, Province of China
Duration: 19 Apr 200924 Apr 2009

Publication series

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

Conference

Conference2009 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2009
Country/TerritoryTaiwan, Province of China
CityTaipei
Period19/04/0924/04/09

Keywords

  • Beta divergence
  • Itakura-Saito (IS) divergence
  • Music transcription
  • Non-negative matrix factorization (NMF)

Fingerprint

Dive into the research topics of 'A tempering approach for Itakura-Saito non-negative matrix factorization. With application to music transcription'. Together they form a unique fingerprint.

Cite this