Subject: SiSEC 2008: try your source separation algorithm now From: Emmanuel Vincent <emmanuel.vincent@xxxxxxxx> Date: Tue, 5 Aug 2008 18:16:21 +0200 List-Archive:<http://lists.mcgill.ca/scripts/wa.exe?LIST=AUDITORY>1st Community-based Signal Separation Evaluation Campaign (SiSEC 2008) http://sisec.wiki.irisa.fr/ Submission deadline: October 31, 2008 SiSEC is the first community-based endeavor for the evaluation of source separation algorithms. Following a first call, four datasets have been proposed by researchers in the field: - Under-determined speech and music mixtures - Determined and over-determined speech mixtures - Head-geometry mixtures of two speech sources in real environments - Professionally produced music recordings Help make this evaluation the most complete yet by trying your source separation algorithms over one or more datasets and submitting the results. To download the datasets and view submission guidelines and evaluation procedures, see http://sisec.wiki.irisa.fr/. Best regards, Emmanuel Vincent, Shoko Araki and Pau Bofill