Multichannel harmonic and percussive component separation by joint modeling of spatial and spectral continuity

Ngoc Duong; Hideyuki Tachibana; Emmanuel Vincent; Nobutaka Ono; Rémi Gribonval; Shigeki Sagayama

inria-00557145, version 2

Multichannel harmonic and percussive component separation by joint modeling of spatial and spectral continuity

Ngoc Duong ( Author to contact preferably )^a^, 1, Hideyuki Tachibana^b^, 2, Emmanuel Vincent^a^, 1, Nobutaka Ono^b^, 2, Rémi Gribonval^a^, 1, Shigeki Sagayama^b^, 2

Acoustics, Speech and Signal Processing, IEEE Conference on (ICASSP'11) (2011)

Abstract: This paper considers the blind separation of the harmonic and percussive components of multichannel music signals. We model the contribution of each source to all mixture channels in the time-frequency domain via a spatial covariance matrix, which encodes its spatial characteristics, and a scalar spectral variance, which represents its spectral structure. We then exploit the spatial continuity and the different spectral continuity structures of harmonic and percussive components as prior information to derive maximum a posteriori (MAP) estimates of the parameters using the expectation-maximization (EM) algorithm. Experimental results over professional musical mixtures show the effectiveness of the proposed approach.

a – INRIA
b – Department of Information Physics and Computing, Graduate School of Information Science and Technology, The University of Tokyo
1: METISS (INRIA - IRISA)
CNRS : UMR6074 – INRIA – Institut National des Sciences Appliquées (INSA) - Rennes – Université de Rennes 1
2: University of Tokyo
University of Tokyo

inria-00557145, version 2
http://hal.inria.fr/inria-00557145
oai:hal.inria.fr:inria-00557145
From: Ngoc Duong <>
Submitted on: Monday, 16 May 2011 16:26:00
Updated on: Friday, 30 September 2011 11:59:32

See detailed view

Associated documents

PDF :

DOI: 10.1109/ICASSP.2011.5946376

Export

Bibtex EndNote TEI RefWorks

<?xml version="1.0" encoding="UTF-8"?>
<listBibl xmlns="http://www.tei-c.org/ns/1.0" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML">
<listBibl type="inproceedings"><head>Peer-reviewed conferences/proceedings</head>
<biblStruct type="inproceedings" xml:id="inria-00557145"><analytic>
<author><persName><forename>Ngoc</forename><surname>Duong</surname></persName>
<affiliation>
<orgName type="laboratory">INRIA - IRISA</orgName>
<orgName type="team">METISS</orgName>
<country>FR</country>
<orgName type="institution">CNRS : UMR6074</orgName>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">Institut National des Sciences Appliquées (INSA) - Rennes</orgName>
<orgName type="institution">Université de Rennes 1</orgName>
</affiliation>
</author>
<author><persName><forename>Hideyuki</forename><surname>Tachibana</surname></persName>
<affiliation>
<orgName type="team">University of Tokyo</orgName>
<country>JP</country>
<orgName type="institution">University of Tokyo</orgName>
</affiliation>
</author>
<author><persName><forename>Emmanuel</forename><surname>Vincent</surname></persName>
<affiliation>
<orgName type="laboratory">INRIA - IRISA</orgName>
<orgName type="team">METISS</orgName>
<country>FR</country>
<orgName type="institution">CNRS : UMR6074</orgName>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">Institut National des Sciences Appliquées (INSA) - Rennes</orgName>
<orgName type="institution">Université de Rennes 1</orgName>
</affiliation>
</author>
<author><persName><forename>Nobutaka</forename><surname>Ono</surname></persName>
<affiliation>
<orgName type="team">University of Tokyo</orgName>
<country>JP</country>
<orgName type="institution">University of Tokyo</orgName>
</affiliation>
</author>
<author><persName><forename>Rémi</forename><surname>Gribonval</surname></persName>
<affiliation>
<orgName type="laboratory">INRIA - IRISA</orgName>
<orgName type="team">METISS</orgName>
<country>FR</country>
<orgName type="institution">CNRS : UMR6074</orgName>
<orgName type="institution">INRIA</orgName>
<orgName type="institution">Institut National des Sciences Appliquées (INSA) - Rennes</orgName>
<orgName type="institution">Université de Rennes 1</orgName>
</affiliation>
</author>
<author><persName><forename>Shigeki</forename><surname>Sagayama</surname></persName>
<affiliation>
<orgName type="team">University of Tokyo</orgName>
<country>JP</country>
<orgName type="institution">University of Tokyo</orgName>
</affiliation>
</author>
<title type="main" level="a">Multichannel harmonic and percussive component separation by joint modeling of spatial and spectral continuity</title></analytic><monogr><meeting>Acoustics, Speech and Signal Processing, IEEE Conference on (ICASSP'11)</meeting><imprint><pubPlace><settlement>Prague</settlement><country>Czech Republic</country></pubPlace><biblScope type="publicationDate">2011-01-18</biblScope></imprint></monogr><idno type="doi">10.1109/ICASSP.2011.5946376</idno><idno type="HALid">http://hal.inria.fr/inria-00557145</idno><idno type="HALFile">http://hal.inria.fr/inria-00557145/PDF/icassp2011_2.pdf</idno></biblStruct>
</listBibl>
</listBibl>