Music Recognition -- Rebirth for the Speech Recognition Set?

Submitted by BruceCyr on Fri, 05/04/2007 - 00:48.

General SR

ScienceNews has an interesting overview of developments in music recognition (MR). At a high level its like SR, but the details are a lot different:

"[A]n informatics researcher at the University of Indiana in Bloomington, compares the problem to speech recognition. 'There's been a veritable army of people who've worked on speech recognition for several decades, and [the problem] still remains open,' he says. 'Any time you deal with real data, there is a huge amount of variation that you have to understand.'"

One of the leading developers, who wrote a program that uses machine learning to "learn" music, began his research career in SR:

http://sciencenews.org/articles/20070421/bob8.asp

PS: Better hurry if you want to catch this link -- it was in last week's edition, so I think access will close sooner rather than later.

If you're really interested

Submitted by Matt Chambers on Fri, 05/04/2007 - 14:09.

If you're really interested in this topic, you might enjoy reading "This is Your Brain on Music", by Levitin.

Thanks, Matt, might be worth

Submitted by BruceCyr on Fri, 05/04/2007 - 20:45.

Thanks, Matt, might be worth a look. I can heartily recommend Robert Greenberg's lectures for the Teaching Company (teach12.com), which is music appreciation on designer steroids. This guy is both a composer and music historian, and shows up on NPR. He was featured in the "middle column" of the WSJ for being hired to add a dollop of culture to monochromatic MBA's in corporate America. Plus the Teaching Company has a local origin for you and me -- it "was founded in 1990 by Thomas M. Rollins, former Chief Counsel of the United States Senate Committee on Labor and Human Resources"