How Google is using AI to create completely new musical sounds

NSynth uses neural networks to combine different kinds of instruments like, say, classical music's clavichord and the Hammond organ of rhythm and blues

Rainbowgrams of audio produced with NSynth.

Google is using artificial intelligence to create musical sounds that human ears have never heard before, said Cade Metz at Wired​. NSynth uses neural networks to combine different kinds of instruments like, say, classical music's clavichord and the Hammond organ of rhythm and blues. NSynth doesn't layer the sounds on top of each other, but uses the mathematical characteristics of the notes generated by each instrument to produce entirely new sounds. And it "can do this with about a thousand different instruments — from violins to balafons."

(Image credit: Google Magenta)

NSynth is the work of Google Magenta, a small team of researchers within the tech giant who are teaching computers how to make art on their own and are creating a wider range of tools for human artists in the process. "Artistically, it could yield some cool stuff," said music critic Marc Weidenbaum. "And because it's Google, people will follow their lead."

Subscribe to The Week

Escape your echo chamber. Get the facts behind the news, plus analysis from multiple perspectives.

SUBSCRIBE & SAVE
https://cdn.mos.cms.futurecdn.net/flexiimages/jacafc5zvs1692883516.jpg

Sign up for The Week's Free Newsletters

From our morning news briefing to a weekly Good News Newsletter, get the best of The Week delivered directly to your inbox.

From our morning news briefing to a weekly Good News Newsletter, get the best of The Week delivered directly to your inbox.

Sign up
To continue reading this article...
Continue reading this article and get limited website access each month.
Get unlimited website access, exclusive newsletters plus much more.
Cancel or pause at any time.
Already a subscriber to The Week?
Not sure which email you used for your subscription? Contact us