Source separation

I’ve just seen some demos of source separation[1] and I’m impressed. Does anyone knows anything about it?

[1] http://cnl.salk.edu/~tewon/Blind/blind_audio.html

More info: http://www.endolith.com/wordpress/2009/11/22/a-simple-fastica-example/

Wow, that is impressive!!

More demos on source separation: http://www.cs.illinois.edu/~paris/demos/