Genre specific dictionaries for harmonic/percussive source separation

Clément Laroche, Hélène Papadopoulos, Matthieu Kowalski, Gaël Richard

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

Abstract

Blind source separation usually obtains limited performance on real and polyphonic music signals. To overcome these limitations, it is common to rely on prior knowledge under the form of side information as in Informed Source Separation or on machine learning paradigms applied on a training database. In the context of source separation based on factorization models such as the Non-negative Matrix Factorization, this supervision can be introduced by learning specific dictionaries. However, due to the large diversity of musical signals it is not easy to build sufficiently compact and precise dictionaries that will well characterize the large array of audio sources. In this paper, we argue that it is relevant to construct genre-specific dictionaries. Indeed, we show on a task of harmonic/percussive source separation that the dictionaries built on genre-specific training subsets yield better performances than cross-genre dictionaries.

Original languageEnglish
Title of host publicationProceedings of the 17th International Society for Music Information Retrieval Conference, ISMIR 2016
EditorsMichael I. Mandel, Johanna Devaney, Douglas Turnbull, George Tzanetakis
PublisherInternational Society for Music Information Retrieval
Pages407-413
Number of pages7
ISBN (Electronic)9780692755068
Publication statusPublished - 1 Jan 2016
Externally publishedYes
Event17th International Society for Music Information Retrieval Conference, ISMIR 2016 - New York, United States
Duration: 7 Aug 201611 Aug 2016

Publication series

NameProceedings of the 17th International Society for Music Information Retrieval Conference, ISMIR 2016

Conference

Conference17th International Society for Music Information Retrieval Conference, ISMIR 2016
Country/TerritoryUnited States
CityNew York
Period7/08/1611/08/16

Fingerprint

Dive into the research topics of 'Genre specific dictionaries for harmonic/percussive source separation'. Together they form a unique fingerprint.

Cite this