Music Genome Project
Encyclopedia
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 Pandora Media to bring their idea to market. The Music Genome Project was an effort to "capture the essence of music
at the fundamental level" using almost 400 attributes to describe songs and a complex mathematical algorithm
to organize them. Under the direction of Nolan Gasser
, the musical structure and implementation of the Music Genome Project, made up of 5 Genomes (Pop/Rock, Hip-Hop/Electronica, Jazz, World Music, and Classical), was advanced and codified.
A given song is represented by a vector
(a list of attributes) containing approximately 400 "genes" (analogous
to trait-determining gene
s for organisms in the field of genetics
). Each gene corresponds to a characteristic of the music, for example, gender of lead vocalist, 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 300–500 genes. The system depends on a sufficient number of genes to render useful results. Each gene is assigned a number between 1 and 5, in half-integer increments.
Given the vector of one or more songs, a list of other similar songs is constructed using a distance function. Each song is analyzed by a musician in a process that takes 20 to 30 minutes per song. Ten percent of songs are analyzed by more than one technician to ensure conformity with the in-house standards and statistical reliability
. The technology is currently used by Pandora
to play music for Internet users based on their preferences. Because of licensing restrictions, Pandora is available only to users whose location is reported to be in the USA by Pandora's geolocation
software.
in the United States. The mark is owned by Pandora Media, Inc.
The Music Genome Project is covered by United States Patent No. 7,003,515. This patent 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 by the holders to Pandora Media, Inc.
The full list of attributes for individual songs are not publicly released, and ostensibly constitutes a trade secret
.
Tim Westergren
Timothy Brooks Westergren , is a co-founder of Pandora Radio.-Biography:He was born on December 21, 1965 in Minneapolis, Minnesota. Westergren graduated from Stanford University with a B.A. in political science...
in late 1999. In January 2000, they joined forces with Jon Kraft to found Pandora Media to bring their idea to market. The Music Genome Project was an effort to "capture the essence of music
Music
Music is an art form whose medium is sound and silence. Its common elements are pitch , rhythm , dynamics, and the sonic qualities of timbre and texture...
at the fundamental level" using almost 400 attributes to describe songs and a complex mathematical algorithm
Algorithm
In mathematics and computer science, an algorithm is an effective method expressed as a finite list of well-defined instructions for calculating a function. Algorithms are used for calculation, data processing, and automated reasoning...
to organize them. Under the direction of Nolan Gasser
Nolan Gasser
Nolan Ira Gasser is an American composer, pianist, and musicologist. He is the Chief Musicologist for Pandora Media, Inc. and the architect of the Music Genome Project, the proprietary musical analysis system that underlies the popular Internet radio service...
, the musical structure and implementation of the Music Genome Project, made up of 5 Genomes (Pop/Rock, Hip-Hop/Electronica, Jazz, World Music, and Classical), was advanced and codified.
A given song is represented by a vector
Coordinate vector
In linear algebra, a coordinate vector is an explicit representation of a vector in an abstract vector space as an ordered list of numbers or, equivalently, as an element of the coordinate space Fn....
(a list of attributes) containing approximately 400 "genes" (analogous
Analogy
Analogy is a cognitive process of transferring information or meaning from a particular subject to another particular subject , and a linguistic expression corresponding to such a process...
to trait-determining gene
Gene
A gene is a molecular unit of heredity of a living organism. It is a name given to some stretches of DNA and RNA that code for a type of protein or for an RNA chain that has a function in the organism. Living beings depend on genes, as they specify all proteins and functional RNA chains...
s for organisms in the field of genetics
Genetics
Genetics , a discipline of biology, is the science of genes, heredity, and variation in living organisms....
). Each gene corresponds to a characteristic of the music, for example, gender of lead vocalist, level of distortion on the electric guitar, type of background vocals, etc. Rock
Rock music
Rock music is a genre of popular music that developed during and after the 1960s, particularly in the United Kingdom and the United States. It has its roots in 1940s and 1950s rock and roll, itself heavily influenced by rhythm and blues and country music...
and pop
Pop music
Pop music is usually understood to be commercially recorded music, often oriented toward a youth market, usually consisting of relatively short, simple songs utilizing technological innovations to produce new variations on existing themes.- Definitions :David Hatch and Stephen Millward define pop...
songs have 150 genes, rap songs have 350, and jazz
Jazz
Jazz is a musical style that originated at the beginning of the 20th century in African American communities in the Southern United States. It was born out of a mix of African and European music traditions. From its early development until the present, jazz has incorporated music from 19th and 20th...
songs have approximately 400. Other genres of music, such as world
World music
World music is a term with widely varying definitions, often encompassing music which is primarily identified as another genre. This is evidenced by world music definitions such as "all of the music in the world" or "somebody else's local music"...
and classical
Classical music
Classical music is the art music produced in, or rooted in, the traditions of Western liturgical and secular music, encompassing a broad period from roughly the 11th century to present times...
music, have 300–500 genes. The system depends on a sufficient number of genes to render useful results. Each gene is assigned a number between 1 and 5, in half-integer increments.
Given the vector of one or more songs, a list of other similar songs is constructed using a distance function. Each song is analyzed by a musician in a process that takes 20 to 30 minutes per song. Ten percent of songs are analyzed by more than one technician to ensure conformity with the in-house standards and statistical reliability
Reliability (statistics)
In statistics, reliability is the consistency of a set of measurements or of a measuring instrument, often used to describe a test. Reliability is inversely related to random error.-Types:There are several general classes of reliability estimates:...
. The technology is currently used by Pandora
Pandora (music service)
Pandora Radio is an automated music recommendation service and custodian of the Music Genome Project available only in the United States. The service plays musical selections similar to song suggestions entered by a user...
to play music for Internet users based on their preferences. Because of licensing restrictions, Pandora is available only to users whose location is reported to be in the USA by Pandora's geolocation
Geolocation
Geolocation is the identification of the real-world geographic location of an object, such as a radar, mobile phone or an Internet-connected computer terminal...
software.
Intellectual property
"Music Genome Project" is a registered trademarkTrademark
A trademark, trade mark, or trade-mark is a distinctive sign or indicator used by an individual, business organization, or other legal entity to identify that the products or services to consumers with which the trademark appears originate from a unique source, and to distinguish its products or...
in the United States. The mark is owned by Pandora Media, Inc.
The Music Genome Project is covered by United States Patent No. 7,003,515. This patent 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 by the holders to Pandora Media, Inc.
The full list of attributes for individual songs are not publicly released, and ostensibly constitutes a trade secret
Trade secret
A trade secret is a formula, practice, process, design, instrument, pattern, or compilation of information which is not generally known or reasonably ascertainable, by which a business can obtain an economic advantage over competitors or customers...
.
See also
- List of Music Genome Project attributes
- MoodbarMoodbarMoodbar is a computer visualization used for navigating within a piece of music. This is done with a horizontal bar that is divided into vertical stripes. Each stripe has a colour showing the "mood" within a short part of the song. The colour can depend on spectrum and/or rhythmic features of the...
- MusicBrainzMusicBrainzMusicBrainz is a project that aims to create an open content music database. Similar to the freedb project, it was founded in response to the restrictions placed on the CDDB...
- Pandora Radio
- WhoSampledWhoSampledWhoSampled is a website and database of information about sample-based music founded in London, United Kingdom.WhoSampled is an online sample-based music databases of music that compares original songs with covered songs or songs that "borrowed" samples, it serves as a historical line of where...
Further reading
- The Song Decoders at Pandora - NYTimes.com October 14, 2009
External links
- "The Music Genome Project" — short historical statement by Tim Westergren
- Patent Number 7003515 — Consumer item matching method and system
- Inside the Net Interview with Tim Westergren of Pandora Media
- Interview with Tim Westergren March 23, 2007
- Interview with Tim Westergren about the Music Genome Project and Pandora video
- The first music of genes by Jean-claude Perez 1994 SACEM GEN0694