Artificial Intelligence is Used to Create Pop Songs Based on the Style of Famous Artists

Wednesday, September 28, 2016

Artificial Intelligence is Used to Create Pop Songs Based on the Style of Famous Artists


Artificial Intelligence

Scientists at Sony CSL Research Lab in Paris have created the first-ever entire songs in the style of Duke Ellington, George Gershwin and The Beatles composed by artificial intelligence. 


Researchers at Sony in a project led by François Pachet and hosted by the Parisian University Pierre and Marie Curie.have created new pop songs composed using artificial intelligence.

The team used their own Flow Machines software that learns music styles from a huge database of songs. Then, exploiting unique combinations of style transfer, optimization and interaction techniques, it can compose a new piece in any style.

Flow machines


The researchers set up a database called LSDB. It contains about 13000 leadsheet from a lot of different styles and composers mainly jazz and pop about also a lot of Brazilian, Broadway and other music styles.

Related articles
Next, a human composer Benoît Carré, selected a style and generated melodies and harmonies with a system called FlowComposer. For example, Carré chose a Beatles style for the song "Daddy's Car." Then, using another system called Rechord the human musicians matched some audio chunks from audio recordings of other songs to the generated more melodies and harmonies.

Human musicians were used for the final production and mixing. Another song, "Mister Shadow" was composed in the style of American songwriters Irving Berlin, Duke Ellington, George Gershwin and Cole Porter. Carré arranged and produced the songs, and wrote the lyrics.

Below, try listening to “Daddy’s Car”, a pop song in the style of The Beatles. The songs will be featured on albums composed by artificial intelligence to be released in 2017.




SOURCE  Flow Machnies


By  33rd Square Embed