Audio Source Separation
- Underdetermined- speech and music mixtures [modified Feb.25]
- Determined and over-determined speech and music mixtures
- Professionally produced music recordings
- Source separation in the presence of real-world background noise [modified Apr.18]
About the tasks, evaluation criteria, potential participants etc., please refer each task site.
The proposal deadline is January 15th, 2010, and its dataset deadline is January 29th, 2010 (Closed).
We welcome other tasks/datasets/evaluation criteria from participants.
Participants who can provide tasks/datasets/evaluation, please contact Shoko Araki (Evaluation Chair member):
- E-mail: shoko (a) cslab.kecl.ntt.co.jp