Google always seems to be innovating in some way or another and this time they’ve set their sights on music.

As we speak, they’re in the process of creating an Artificial Intelligence synthesizer program. It goes by the name of NSynth (Ha like NSYNC, get it?) short for Neural Synthesizer.

It’s in development by the team at Google Magenta and works by analyzing instrumental samples and creating new sounds based off the mathematical components of of instruments and their respective note values. I’m not too sure what that means, but here’s more jargon from the Magenta team themselves:

“Unlike a traditional synthesizer which generates audio from hand-designed components like oscillators and wavetables, NSynth uses deep neural networks to generate sounds at the level of individual samples. Learning directly from data, NSynth provides artists with intuitive control over timbre and dynamics and the ability to explore new sounds that would be difficult or impossible to produce with a hand-tuned synthesizer”.

You can check out some weird instrumental samples below that they’ve come across. Tell us what you think about the project, is Skynet going too far?

[Via: Dancing Astronaut]