Canal de syndication RSS Tiki pour les pages Wiki http://sisec2008.wiki.irisa.fr/tiki-wiki_rss.php?ver=2 Fri, 06 Nov 2015 15:44:27 +0100 Tiki CMS/Groupware via FeedCreator 1.7.2.1 http://sisec2008.wiki.irisa.fr/img/tiki/tikilogo.png SiSEC 2008 http://sisec2008.wiki.irisa.fr/tiki-index.php en-us Professionally produced music recordings http://sisec2008.wiki.irisa.fr/tiki-index.php?page=Professionally+produced+music+recordings .diffchar { color:red; } - MarC Nxx Rs
+ M. Nxx
- Task proposed by: MarC Nxx Rs
+ Task proposed by: M. Nxx
]]> Wed, 18 Sep 2013 16:14:04 +0100 HomePage http://sisec2008.wiki.irisa.fr/tiki-index.php?page=HomePage .diffchar { color:red; } +
+

Reference papers

+ Results are summarized in the following reference papers
+
+ +
+ -
- The 8th International Conference on Independent Component Analysis and Signal Separation (external link) (ICA 2009) will feature a special session on SiSEC 2008. In addition, entrants not wishing to submit a paper will have the opportunity to present a poster about their approach. No selection will be carried out: all posters are welcome, including those previously presented at other conferences.
-
- We are also thinking of organizing a workshop early 2009 promoting further discussion of evaluation methodology and combination of several algorithms. Let us know if you are interested.
]]> Wed, 21 Mar 2012 17:18:59 +0100 title for building http://sisec2008.wiki.irisa.fr/tiki-index.php?page=title+for+building .diffchar { color:red; } + content for building
]]> Sun, 24 Jul 2011 19:41:06 +0100 Determined and over-determined speech and music mixtures http://sisec2008.wiki.irisa.fr/tiki-index.php?page=Determined+and+over-determined+speech+and+music+mixtures .diffchar { color:red; } + These files are licensed for research use only by their authors (see list of authors below).
]]> Fri, 19 Feb 2010 08:49:15 +0100 Head-geometry mixtures of two speech sources in real environments, impinging from many directions http://sisec2008.wiki.irisa.fr/tiki-index.php?page=Head-geometry+mixtures+of+two+speech+sources+in+real+environments%2C+impinging+from+many+directions .diffchar { color:red; } + These files are made available under the terms of the Creative Commons Attribution-NonCommercial-ShareAlike 2.0 (external link) license. The authors of the dataset are Hendrik Kayser and Jörn Anemüller. The collection of the dataset was supported by the European Commission under IP DIRAC.
- For each recording, the sources are located on a circle around the receiver in a fixed distance. In the anechoic chamber, the distance from source to receiver is 3 meters and the source position is varied in a full circle in steps of 20°. This yields 18 stereo signals per source. In the office room, the distance is 1 meter and the source positions are on the front hemisphere of the artificial head, ranging from 90° to the left to 90° to the right in steps of 10°, yielding 19 stereo signals per source.
+ For each recording, the sources are located on a circle around the receiver in a fixed distance. In the anechoic chamber, the distance from source to receiver is 3 meters and the source position is varied in a full circle in steps of 20°. This yields 18 stereo signals per source. In the office room, the distance is 1 meter and the source positions are on the front hemisphere of the artificial head, ranging from 90° to the left to 90° to the right in steps of 10°, yielding 19 stereo signals per source.
- where <situation> is either ’anechoic’ or ’office’, <pos1> and <pos2> denote the angle of incidence of source one and source two according to the coordinate system (external link) . The sampling frequency is 16 kHz.
+ where <situation> is either 'anechoic' or 'office', <pos1> and <pos2> denote the angle of incidence of source one and source two according to the coordinate system (external link) . The sampling frequency is 16 kHz.
+ These files are made available under the terms of the Creative Commons Attribution-NonCommercial-ShareAlike 2.0 (external link) license. The authors of the dataset are Hendrik Kayser and Jörn Anemüller. The collection of the dataset was supported by the European Commission under IP DIRAC.
-
  • Jörn Anemüller (joern.anemueller (a) uni-oldenburg_de)+
    • Jörn Anemüller (joern.anemueller (a) uni-oldenburg_de)- Task proposed by: Hendrik Kayser, Jörn Anemüller

      Support by the European Commission under integrated project DIRAC (Detection and Identification of Rare Audio-visual Cues) IST-027787 is gratefully acknowledged. Thanks to Volker Hohmann, Stephan Ewert and Thomas Rohdenburg who have made significant contributions to the developement and implementation of the measurement techniques and for the support by HörTech%83%C2%B6rTech" title="Créer une page : H%C3%83%C2%B6rTech" class="wiki wikinew">?, the German centre of competence on hearing technology.
      + Task proposed by: Hendrik Kayser, Jörn Anemïller

      Support by the European Commission under integrated project DIRAC (Detection and Identification of Rare Audio-visual Cues) IST-027787 is gratefully acknowledged. Thanks to Volker Hohmann, Stephan Ewert and Thomas Rohdenburg who have made significant contributions to the developement and implementation of the measurement techniques and for the support by HörTech?, the German centre of competence on hearing technology.
      ]]> Fri, 19 Feb 2010 08:45:45 +0100 Under-determined speech and music mixtures http://sisec2008.wiki.irisa.fr/tiki-index.php?page=Under-determined+speech+and+music+mixtures .diffchar { color:red; } + These files are made available under the terms of the Creative Commons Attribution-NonCommercial-ShareAlike 2.0 (external link) license. The authors are Glen Phillips, Mark Engelberg, Psycho Voyager, Nine Inch Nails and Ali Farka Touré for music source signals and Shoko Araki and Emmanuel Vincent for mixture signals.
      + These files are made available under the terms of the Creative Commons Attribution-NonCommercial-ShareAlike 2.0 (external link) license. The authors are Another Dreamer and Alex Q for music source signals and Hiroshi Sawada, Shoko Araki and Emmanuel Vincent for mixture signals.
      ]]>       Fri, 19 Feb 2010 08:39:17 +0100       Previous evaluation campaigns http://sisec2008.wiki.irisa.fr/tiki-index.php?page=Previous+evaluation+campaigns .diffchar { color:red; } +

      Previous evaluation campaigns

      +
      + Previous evaluations of signal separation algorithms include
      + ]]>       Wed, 30 Apr 2008 15:54:44 +0100       Panel discussion at ICA'07 http://sisec2008.wiki.irisa.fr/tiki-index.php?page=Panel+discussion+at+ICA%2707 .diffchar { color:red; } +

      Panel discussion at ICA'07

      +
      + A panel discussion about evaluation was held at the ICA'07 (external link) conference. The main recommendations of the audience regarding future evaluations include
      +
      • splitting the signal separation problem into several connected tasks that may be solved individually or simultaneously+
      • providing reference software for each task+
      • allowing different separation outputs, e.g. original source signals or their contribution to the mixture signal+
      • considering real-world data of interest to companies, e.g. time-varying mixtures with one prominent speech source to be enhanced, music mixed in a studio+
      ]]>       Mon, 25 Feb 2008 13:08:53 +0100