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...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Signal processing Ročník 92; číslo 8; s. 1928 - 1936
Hlavní autoři: Vincent, Emmanuel, Araki, Shoko, Theis, Fabian, Nolte, Guido, Bofill, Pau, Sawada, Hiroshi, Ozerov, Alexey, Gowreesunker, Vikrham, Lutter, Dominik, Duong, Ngoc Q.K.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier B.V 01.08.2012
Elsevier
Témata:
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
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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).
Bibliografie: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