U.S. Endorses Music Search Project

    August 14, 2007

We all know that Google can help us find MP3 files, but the leading search engine just works off of words and phrases.  Another engine would actually listen to and analyze music, and it just received a small amount of funding from the U.S. National Science Foundation.

The funding may be more of a vote of confidence than a financial boost; after seeing millions of dollars tossed around on a daily basis, the odd sum of $99,564 doesn’t look like much.  Still, that’s not a bad start for the SGER project, which is being run by the College of Charleston.

“This SGER project aims to develop a prototype music search engine based on identifying aesthetic similarities,” according to an “Award Abstract.”  “This engine will utilize power-law metrics to extract statistical proportions of music-theoretic and other attributes of music pieces (e.g., Pitch, Duration, Pitch Distance, Duration Distance, Melodic Intervals, Harmonic Intervals, Melodic Bigrams, etc.).”

Or, to put that into more comprehensible language, “The engine searches for pieces that are aesthetically similar to the input piece . . . .”

That would be nifty – supply SGER with one song you like, and it might provide you with a hundred great artists you’ve never heard of.  It also, to be honest, sounds a little farfetched.  But the abstract reveals, “Preliminary testing has been done using the Classical Music Archives corpus (14,695 MIDI pieces), combined with 500+ MIDI pieces from other styles (e.g. Jazz, Rock, Country, etc.).”

The abstract also lists an estimated “expiration date” as July 31, 2009, however, so it could be quite some time before we see (or hear) any results from SGER.  Hat tip to John Battelle.