Tuesday, June 22, 2010

Music Search Researchers in New Scientist

A NewScientist story called "Computerised critics could find the music you'll like," highlights the music annotation and related music-meets-machine-learning research being done here at the Jacobs School.

The reporter, MacGregor Campbell, talks to electrical engineering (ECE) graduate student Luke Barrington about the research described in the From a Queen Song to a Better Music Search Engine story from last year.

From the NewScientist story:
Barrington is building software that can analyse a piece of music and distil information about it that may be useful for software trying to compile a playlist. With this information, the software can assign the music a genre or even give it descriptions which may appear more subjective, such as whether or not a track is "funky", he says.
This work is being done in the Computer Audition Laboratory, which is led by ECE professor Gert Lanckriet.

No comments: