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

  • Authors:
  • Emmanuel Vincent;Shoko Araki;Fabian Theis;Guido Nolte;Pau Bofill;Hiroshi Sawada;Alexey Ozerov;Vikrham Gowreesunker;Dominik Lutter;Ngoc Q. K. Duong

  • Affiliations:
  • INRIA, Centre de Rennes-Bretagne Atlantique, 35042 Rennes Cedex, France;NTT Communication Science Labs, NTT Corporation, 2-4 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237, Japan;Institute for Bioinformatics and Systems Biology, Helmholtz Zentrum München, Ingolstädter Landstraíe, 85764 Neuherberg, Germany;Fraunhofer FIRST.IDA, Kekuléstrasse 7, 12489 Berlin, Germany;Department of Computer Architecture, Universitat Politècnica de Catalunya, Campus Nord Mòdul D6, Jordi Girona 1-3, 08034 Barcelona, Spain;NTT Communication Science Labs, NTT Corporation, 2-4 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0237, Japan;INRIA, Centre de Rennes-Bretagne Atlantique, 35042 Rennes Cedex, France;DSP Solutions R&D Center, Texas Instruments Inc., 12500 TI Boulevard, MS 8649, Dallas, TX 75243, USA;Institute for Bioinformatics and Systems Biology, Helmholtz Zentrum München, Ingolstädter Landstraíe, 85764 Neuherberg, Germany;INRIA, Centre de Rennes-Bretagne Atlantique, 35042 Rennes Cedex, France

  • Venue:
  • Signal Processing
  • Year:
  • 2012

Quantified Score

Hi-index 0.08

Visualization

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).