Music Genome Project

From Wikipedia, the free encyclopedia

The Music Genome Project, created in January 2000, is an effort founded by Tim Westergren, a 1988 graduate from Stanford University and spearheaded by a group of musicians and technicians to "capture the essence of music at the fundamental level" by using over 400 attributes to describe songs.

All songs are analyzed by a music analyst in a process that takes 20 to 30 minutes per song. Each gene is rated on a scale of 1 to 5. Ten percent of songs are analyzed by more than one technician to ensure conformity with the standards.

The technology is currently used by Pandora to play music for Internet users based on their preferences. Users are invited to create "radio stations" by entering artists or song titles. Pandora then uses an algorithm to select and play music similar to the users' selections. Since the algorithm selects songs on the basis of musical features, rather than artist popularity or record sales, many users have lauded Pandora for its ability to "recommend" unfamiliar songs that fit a user's preferences. Obscure artists may submit their music to the Music Genome Project in a bid to become better known.

[edit] See also

[edit] Reference

"The Music Genome Project" - short historical statement by Tim Westergren

[edit] External links

Pandora
Interview - Inside the Net Interview with Tim Westergren of Pandora Media
Pandora's Box - East Bay Express article on music classification
Download Squad - Interview with Tim Westergren about the Copyright Royalty Board planned fee increase for internet radio operators