AI Business is part of the Informa Tech Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 3099067.

Google Brain is Creating Sounds We've Never Heard Before With AI

by
 
Article Image

A team inside Google Brain has developed an AI algorithm, NSynth, which is capable of creating sounds never before heard by our ears.

Researchers have been doing all sorts of weird and wonderful things with AI, ranging from directing adverts to creating a bonafide AI composer. Researchers have opened up the world to a plethora of new possibilities through AI, however the technology is still untapped, and there's so much more to come.

That said, a small team of researchers inside Google's deep learning artificial intelligence research lab, known as Google Brain, have developed an AI that can create new sounds by being fed samples of real-life instruments (organs, flutes, basses, etc).

The results are strange, even eerie, but Nsnyth (Neural Synthesizer), which is what the team has dubbed the project, has created its own sound completely new to our human ears. Things get particularly interesting when the different sounds are then combined and spawn something completely new.

Two of the researchers behind this project, Jesse Engel and Cinjon Resnick, are part of the team who developed this AI algorithm, and will demo the technology publicly for the first time later this week at Moogfest, an annual art, music, and technology festival.

Google first unveiled the project in a blog post published last month, and the company claimed that NSynth will open up musicians to an entirely new world of creating music. In an interview with WIRED, music critic Mark Weidenbaum pointed out that “artistically, it could yield some cool stuff, and because it’s Google, people will follow their lead.”

You can listen to the sounds of NSynth below

[soundcloud url="https://api.soundcloud.com/tracks/322764058" params="color=ff5500&auto_play=false&hide_related=false&show_comments=true&show_user=true&show_reposts=false" width="100%" height="166" iframe="true" /]

 

[soundcloud url="https://api.soundcloud.com/tracks/322763916" params="color=ff5500&auto_play=false&hide_related=false&show_comments=true&show_user=true&show_reposts=false" width="100%" height="166" iframe="true" /]

 

[soundcloud url="https://api.soundcloud.com/tracks/322763432" params="color=ff5500&auto_play=false&hide_related=false&show_comments=true&show_user=true&show_reposts=false" width="100%" height="166" iframe="true" /]

Trending Stories
All Upcoming Events

Upcoming Webinars

More Webinars

Latest Videos

More videos

EBooks

More EBooks

Research Reports

More Research Reports
AI Knowledge Hub

AI for Everything Series

Oge Marques explaining recent developments in AI for Radiology

Author of the forthcoming book, AI for Radiology

AI Knowledge Hub

Newsletter Sign Up


Sign Up