NSynth: Google’s New Way of Making Music

Written by Liz Quirk

Artificial Intelligence (AI) is making its way into all aspects of technology, from wearables to enterprise software.

As a part of Google’s new AI Experiments collection, they created AutoDraw: the first AI-powered Microsoft Paint. This app combines conventional doodling with art from professionals to enhance your drawings and doodles to help create better art.

However, Google is now moving beyond draw and paint, and has its sights set on dominating another art form: music.

Last month, Google’s AI research team, Google Magenta, announced a new project for their AI Experiments collection called Neural Synthesizer (or NSynth).

NSynth generates audio by using deep neural networks and creates music by using a dataset containing sounds from individual instruments, which are then blended together to create hybrid sounds.

According to the tech giant, NSynth gives 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.

Cinjon Resnick, member of the Google Magenta team, said the resulting sound is not like playing two of the individual sounds together. Instead, the software is actually producing an entirely new sound that would be nearly impossible to create otherwise. The end product bears resemblance to sounds that are in between other instruments, combined in a way that can only be done digitally.

Freia Lobo, writer for Mashable, claims the code for this product is open-source, meaning that anyone can download, modify and use it. The Magenta team has already produced some interesting pieces of music.

Several other systems like IBM’s Watson have been working on similar projects for music made for/by AI, but for now, Google itself is not offering the software as a product. NSynth is meant to be a dataset for other developers to play with and attempt creative projects.

But don’t fret musicians! Google’s intention is to make new sounds that are expressive to work WITH you rather than replace musicians.