| HAL-Inria | Publications, software ... of Inria's scientists |
The Signal Separation Evaluation Campaign (2007-2010): Achievements and Remaining Challenges
Emmanuel Vincent
1
Shoko Araki
2
Fabian J. Theis
3
Guido Nolte
4
Pau Bofill
5
Hiroshi Sawada
2
Alexey Ozerov
1
B. Vikrham Gowreesunker
6
Dominik Lutter
7
Ngoc Duong
1
1
METISS - Speech and sound data modeling and processing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Emmanuel Vincent 1
Mail :
Author IdHAL : emmanuelv ORCID : https://orcid.org/0000-0002-0183-7289
Shoko Araki 2
Author
Fabian J. Theis 3
Mail :
Author
Guido Nolte 4
Author
Pau Bofill 5
Author
Hiroshi Sawada 2
Author
Alexey Ozerov 1
Mail :
Author Employer institution : Institut National de Recherche en Informatique et en Automatique
B. Vikrham Gowreesunker 6
Author
Dominik Lutter 7
Author
Ngoc Q. K. Duong 1
Mail :
Author Employer institution : Institut National de Recherche en Informatique et en Automatique
1
METISS - Speech and sound data modeling and processing (Campus de Beaulieu 35042 Rennes cedex - France)
- IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires (Campus universitaire de Beaulieu - 35042 Rennes - France)
- UR1 - Université de Rennes 1 (2 rue du Thabor - CS 46510 - 35065 Rennes cedex - France)
- UNIV-RENNES - Université de Rennes (France)
- INSA Rennes - Institut National des Sciences Appliquées - Rennes (20, avenue des Buttes de Coësmes - CS 70839 - 35708 Rennes cedex 7 - France)
- Inria - Institut National de Recherche en Informatique et en Automatique (Domaine de Voluceau Rocquencourt - BP 105 78153 Le Chesnay Cedex - France)
- CNRS - Centre National de la Recherche Scientifique : UMR6074 (France)
- UR1 - Université de Rennes 1 (2 rue du Thabor - CS 46510 - 35065 Rennes cedex - France)
- Inria Rennes – Bretagne Atlantique (Campus de beaulieu
35042 Rennes cedex - France)
- Inria - Institut National de Recherche en Informatique et en Automatique (Domaine de Voluceau Rocquencourt - BP 105 78153 Le Chesnay Cedex - France)
2
NTT Communication Science Laboratories (2-4 Hikaridai Seika-cho Soraku-gun, Kyoto, 619-0237, Japan - Japan)
- NTT Corporation (Japan)
3
Institute of Bioinformatics and Systems Biology [München] (Helmholtz Zentrum München Ingolstädter Landstraße 1 85764 Neuherberg, Germany - Germany)
- TUM - Technische Universität München [München] (Arcisstraße 21, 80333 München - Germany)
4
IDA - Department Intelligent Data Analysis [Berlin] (Fraunhofer Institute for Computer Architecture and Software Technology FIRST Kekuléstraße 7 12489 Berlin - Germany)
5
DAC-UPC - Department of Computer Architecture [Barcelona] (Campus Nord UPC D6 Building / C6 Building Jordi Girona 1-3 08034 Barcelona - Spain)
- UPC - Universitat Politècnica de Catalunya [Barcelona] (C./Jordi Girona, 1-3, 08034 Barcelona - Spain)
6
Texas Instruments - R&D center [USA] (P.O. Box 660199 Dallas, TX 75266-0199 - United States)
- Texas Instruments (France)
7
IBB - Institute of Biomathematics and Biometry - Helmholtz Zentrum München (Ingolstädter Landstraße 1 D-85764 Neuherberg - Germany)
- HZM - Helmholtz-Zentrum München (Ingolstaedter Landstraße 1, D-85764 Neuherberg - Germany)
Abstract : 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).
Document type :
Journal articles
Complete list of metadatas
https://hal.inria.fr/inria-00630985
Contributor : Emmanuel Vincent <>
Submitted on : Tuesday, October 11, 2011 - 11:17:26 AM
Last modification on : Thursday, March 5, 2020 - 4:56:32 PM
Document(s) archivé(s) le : Thursday, January 12, 2012 - 2:26:02 AM
Contributor : Emmanuel Vincent <>
Submitted on : Tuesday, October 11, 2011 - 11:17:26 AM
Last modification on : Thursday, March 5, 2020 - 4:56:32 PM
Document(s) archivé(s) le : Thursday, January 12, 2012 - 2:26:02 AM
File
vincent_SigPro11.pdf
Files produced by the author(s)
Identifiers
- HAL Id : inria-00630985, version 1
- DOI : 10.1016/j.sigpro.2011.10.007
Collections
CNRS | INRIA | UNIV-RENNES1 | IRISA | IRISA-D5 | UR1-UFR-ISTIC | UNIV-RENNES | INSA-GROUPE
Citation
Emmanuel Vincent, Shoko Araki, Fabian J. Theis, Guido Nolte, Pau Bofill, et al.. The Signal Separation Evaluation Campaign (2007-2010): Achievements and Remaining Challenges. Signal Processing, Elsevier, 2012, 92, pp.1928-1936. ⟨10.1016/j.sigpro.2011.10.007⟩. ⟨inria-00630985⟩
Metrics
Record views
967
Files downloads