Hosted by IDTechEx
Artificial Intelligence Research
Posted on July 16, 2019 by  & 

Machine learning tries to crack disputed Beatles authorship

Researchers at Harvard University and Canada's Dalhousie University used machine learning to ascertain the authorship of disputed Beatles songs.
 
Over a three-year period, the team created an algorithm and applied it to an array of musical motifs taken from 70 songs co-authored by Paul McCartney and John Lennon.
 
The algorithm was able to distinguish tracks known to be written by one of the two musicians with 76% accuracy.
 
When applied to eight disputed songs or song segments, the algorithm found a number of the songs yielded a more than 90% match against Lennon's other works; one song was an 81% match for Lennon, with its bridge returning a 57% match for McCartney.
 
Harvard's Mark Glickman hopes the algorithm's statistical model finds use as "a blueprint for those wanting to follow changes in music over time."
 
Source: Association for Computing Machinery
Top image: Pixabay
More IDTechEx Journals