Google is creating music with machine learning

Share on facebook
Share on twitter
Share on linkedin
Share on telegram
Share on whatsapp

Contents

Overview

  • Google's research arm, Magenta, has developed a deep neural network to generate sound
  • To use the algorithm, has also released an open source hardware instrument called NSynth Super
  • It has been created using libraries like TensorFlow and openFrameworks.
  • They have made the full code public on GitHub so you can create your own instrument from scratch.
  • Watch the videos below for more details.

Introduction

The field of audio processing has attracted great interest with the rise of deep learning. But, What if you find yourself working in the music industry and you are faced with being blocked by a musician (on the same lines as a writer's block)? You have some initial ideas, but the music just doesn't flow to you.

Google also has an answer for that.

Magenta, Google's research arm that finds alternatives to using artificial intelligence to help people's imaginations, has developed an instrument that calls NSynth Super. It is based on the NSynth algorithm that uses a deep neural network technique to generate sound.. NSynth was launched by Google a few months ago.

Instead of generating musical notes, NSynth replicates the sound of an instrument. What makes the algorithm unique is that it continually learns the core qualities of what makes up an individual sound and is able to combine various sounds to generate something absolutely new..

NSynth Super es un instrumento experimental open source. Provides the musicians (and deep learning followers) the ability to explore absolutely new sounds generated by the NSynth machine learning algorithm. It has been created using open source libraries like TensorFlow and openFrameworks.

The instrument can be played via any MIDI source, like a keyboard or sequencer.

You can build your own NSynth Super interface by following the step-by-step code and instructions provided by Google on your GitHub repository.

To dig into the algorithm and get the dataset behind NSynth, go to google blog here.

See NSynth's Google Video below:

Also see how the NSynth Super instrument works below:

Our opinion on this

The instructions given by Google on their GitHub page are detailed and will help you to create the instrument step by step. (Probably) you won't be able to make one as beautiful as Google's, but it will be able to generate crazy sound sequences to start.

This is a gold mine for deep learning enthusiasts who are interested in the field of audio processing.. Ahead, check the code, give it a try and build your own music database!

Subscribe to AVBytes here for regular data science updates, machine learning and artificial intelligence in your inbox.

Subscribe to our Newsletter

We will not send you SPAM mail. We hate it as much as you.