CAN WE TEACH COMPUTERS TO MAKE LIKE MENDELSSOHN?

Monday, December 18, 2017

CAN WE TEACH COMPUTERS TO MAKE LIKE MENDELSSOHN?

Not yet. Robot composer good at emulating short snippets, but still hasn’t mastered melody

Duke researchers are teaching computers to compose new classical music in the style of Romantic-era composers like Chopin and Beethoven. Photo from Pixabay.com

Canon, produced more pleasing tunes.

Computer-generated music isn’t new. Researchers such as David Cope, former professor of music at the University of California, Santa Cruz, have tried to use computers to analyze and imitate musical styles since the early 1980s.

Ultimately, the Duke team is trying to figure out which methods work best for modeling particular types of music. Models developed based on patterns in Romantic-era music may not work as well for jazz, for example.

The researchers concede that the models they tried were trained on a simplified representation of real music. For one, the training data imply that the notes are always played sequentially one after the other, and never simultaneously, as in a chord. But it’s a start.

“In the future we’d also like to look at orchestral pieces with multiple instruments,” said Yanchenko, currently on the staff at MIT Lincoln Laboratory. “But we’re not there yet.”

Yanchenko presented the results on Dec. 7 at the 12th Women in Machine Learning Workshop, held in conjunction with the 2017 Conference on Neural Information Processing Systems in Long Beach, California.

This research was supported by the National Science Foundation (NSF DMS 16-13261, NSF IIS 15-46331, NSF DMS 14-18261, NSF DMS-17-13012, NSF ABI 16-61386) and the National Institutes of Health (NIH R21 AG055777-01A).

CITATION:  "Classical Music Composition Using State Space Models," Anna Yanchenko and Sayan Mukherjeehttps://arxiv.org/abs/1708.03822.