Music Genome Project

The Music Genome Project is an effort to "capture the essence of music at the most fundamental level" using over 450 attributes to describe songs and a complex mathematical algorithm to organize them. The Music Genome Project is currently made up of 5 sub-genomes: Pop/Rock, Hip-Hop/Electronica, Jazz, World Music, and Classical. Under the direction of Nolan Gasser and a team of musicological experts, the initial attributes were later refined and extended.

Recommender systems
Concepts
Methods and challenges
Implementations
Research

A given song is represented by a vector containing values for approximately 450 "genes" (analogous to trait-determining genes for organisms in the field of genetics). Each gene corresponds to a characteristic of the music, for example, gender of lead vocalist, prevalent use of groove, level of distortion on the electric guitar, type of background vocals, etc. Rock and pop songs have 150 genes, rap songs have 350, and jazz songs have approximately 400. Other genres of music, such as world and classical music, have 300–450[1] genes. The system depends on a sufficient number of genes to render useful results. Each gene is assigned a number between 0 and 5, in half-integer increments.[2] The Music Genome Project's database is built using a methodology that includes the use of precisely defined terminology, a consistent frame of reference, redundant analysis, and ongoing quality control to ensure that data integrity remains reliably high.[1]

Given the vector of one or more songs, a list of other similar songs is constructed using what the company calls its "matching algorithm". Each song is analyzed by a musician in a process that takes 20 to 30 minutes per song.[3] Ten percent of songs are analyzed by more than one musician to ensure conformity with the in-house standards and statistical reliability.

The Music Genome Project was first conceived by Will Glaser and Tim Westergren in late 1999. In January 2000, they joined forces with Jon Kraft to found Savage Beast Technologies to bring their idea to market.[4] The Music Genome Project was developed in its entirety by Pandora Media and remains the core technology used for Pandora Radio, its internet radio service. Although there was a time when the company licensed this technology for use by others, today it is limited for use only by its users.

Intellectual property

"Music Genome Project" is a registered trademark in the United States. The mark is owned by the company Pandora Media, Inc.[5]

The Music Genome Project is covered by U.S. Patent 7,003,515 which shows William T. Glaser, Timothy B. Westergren, Jeffrey P. Stearns, and Jonathan M. Kraft as the inventors of this technology. The patent has been assigned to Pandora Media, Inc.

The full list of attributes for individual songs is not publicly released, and ostensibly constitutes a trade secret.

See also

References
  1. "About The Music Genome Project". Pandora Internet Radio. Retrieved 17 August 2014.
  2. U.S. Patent 7,003,515
  3. Ike, Elephant (February 2006). "Tiny Mix Tapes: Tim Westergren Interview". Retrieved 30 May 2013.
  4. Westergren, Tim (March 9, 2009). "VV Show #54 - Tim Westergren of Pandora". Venture Voice (Interview). Interviewed by Greg Galant. Retrieved 2011-06-26.
  5. "Music Genome Project" US Trademark: No. 2731047 United States Patent Office

Further reading
  • Castelluccio, Michael (December 2006), "The Music Genome Project", Strategic Finance, 88 (6): 57–58, ISSN 1524-833X
  • Jennings, David (2007), Net, Blogs and Rock 'N' Roll: How Digital Discovery Works and What it Means for Consumers, Creators and Culture, London, UK; Boston, MA: Nicholas Brealey Pub., ISBN 978-1-85788-398-5, OCLC 145379643
  • John, Joyce (September 2006), "Pandora and the Music Genome Project", Scientific Computing, 23 (10): 14, 40–41, ISSN 1930-5753, archived from the original on 2012-02-16, retrieved 2008-08-03
  • Walker, Rob (October 14, 2009). "The Song Decoders at Pandora". The New York Times. Retrieved November 23, 2012.
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.