[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: separating voices and music in movie scenes

Dear Christian,

Professor D. L. Wang at Ohio State University and his students have working on ASA based singing voice separation for some years and they have a paper in this topic published in IEEE trans. Audio, speech and language processing in 2007. To me, the approach presented in that paper may not match your requirement. I am not sure whether they have any recent progress. Please visit his webpage for more information at http://www.cse.ohio-state.edu/~dwang/.

Best wished,

Nengheng Zheng
----- Original Message ----- From: "Christian Kaernbach" <auditorymail@xxxxxxxxxxxx>
To: <AUDITORY@xxxxxxxxxxxxxxx>
Sent: Monday, January 28, 2008 3:04 PM
Subject: Re: separating voices and music in movie scenes

Dear Pawel and Eero,

Thank you very much for your responses. The "physical" approach (remixing of channels) is one that I did not consider up to now, and which might with some movies really help. We will probably use only very recent movies, as we have found that the degree of familiarity is important for the elicitation of strong emotion. (Believe it or not: many students would not know Casablanca.) The movies would be in Dolby.

What I really thought was that by now auditory scene analysis (ASA) would be advanced far enough to solve this problem. It is simpler than segregating the voice from songs, because it would normally deal with spoken speech (as opposed to sung speech) that is overlayed with instrumental music. I have listened years ago to some demonstration of somebody who presented the result of a computational ASA approach, and it was (as a demo) quite convincing. Unluckily I don't remember the details, nor the name. I have no idea whether such algorithms are by now mature enough to solve such a task.

Christian Kaernbach