The signal separation evaluation campaign (2007–2010): Achievements and remaining challenges

We present the outcomes of three recent evaluation campaigns in the field of audio and biomedical source separation. These campaigns have witnessed a boom in the range of applications of source separation systems in the last few years, as shown by the increasing number of datasets from 1 to 9 and th...

Full description

Saved in:
Bibliographic Details
Published in:Signal processing Vol. 92; no. 8; pp. 1928 - 1936
Main Authors: Vincent, Emmanuel, Araki, Shoko, Theis, Fabian, Nolte, Guido, Bofill, Pau, Sawada, Hiroshi, Ozerov, Alexey, Gowreesunker, Vikrham, Lutter, Dominik, Duong, Ngoc Q.K.
Format: Journal Article
Language:English
Published: Elsevier B.V 01.08.2012
Elsevier
Subjects:
Audio
Biomedical
Boom
Computer programs
Computer Science
Conferences
Engineering Sciences
Evaluation
Methodology
Panels
Resources
Separation
Signal and Image Processing
Signal processing
Software
Source separation
Evaluation
Source separation
Resources
Audio
Biomedical
ISSN:0165-1684, 1872-7557
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present the outcomes of three recent evaluation campaigns in the field of audio and biomedical source separation. These campaigns have witnessed a boom in the range of applications of source separation systems in the last few years, as shown by the increasing number of datasets from 1 to 9 and the increasing number of submissions from 15 to 34. We first discuss their impact on the definition of a reference evaluation methodology, together with shared datasets and software. We then present the key results obtained over almost all datasets. We conclude by proposing directions for future research and evaluation, based in particular on the ideas raised during the related panel discussion at the Ninth International Conference on Latent Variable Analysis and Signal Separation (LVA/ICA 2010).
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0165-1684
1872-7557
DOI:10.1016/j.sigpro.2011.10.007