This campaign aimed to evaluate the performance of source separation algorithms for stereo under-determined mixtures, i.e. two-channel audio signals with three sources or more. Three types of mixtures have been considered:
- instantaneous mixtures (static sources mixed using positive gains)
- synthetic convolutive mixtures (static sources mixed using synthetic room impulse responses)
- live recordings (static sources recorded one at a time in a meeting room and subsequently added together)
Thirteen participants applied fifteen different algorithms to the provided test data and submitted stereo source estimates, consisting of the contribution of each source on the two mixture channels. Both blind and non-blind algorithms were accepted. The results were evaluated using several complementary objective criteria. Additional listening tests are currently planned.
Results are summarized in the following reference papers
- E. Vincent, S. Araki, F.J. Theis, G. Nolte, P. Bofill, H. Sawada, A. Ozerov, B.V. Gowreesunker, D. Lutter and N.Q.K. Duong, "The Signal Separation Evaluation Campaign (2007-2010): Achievements and remaining challenges", Signal Processing, 92, pp. 1928-1936, 2012.
- E. Vincent, H. Sawada, P. Bofill, S. Makino and J.P. Rosca, "First stereo audio source separation evaluation campaign: data, algorithms and results", in Proc. Int. Conf. on Independent Component Analysis and Signal Separation, pp. 552-559, 2007.
January 11, 2007: call for participation
April 13, 2007: submission deadline
April 27, 2007: extended submission deadline
June 1, 2007: publication of the results and objective performance figures
September 12, 2007: special poster session and panel discussion at ICA'07