Hands-On Music Generation with Magenta

By : DuBreuil

4 (3)

Buy this Book

Hands-On Music Generation with Magenta

4 (3)

By: DuBreuil

Buy this Book

Overview of this book

The importance of machine learning (ML) in art is growing at a rapid pace due to recent advancements in the field, and Magenta is at the forefront of this innovation. With this book, you’ll follow a hands-on approach to using ML models for music generation, learning how to integrate them into an existing music production workflow. Complete with practical examples and explanations of the theoretical background required to understand the underlying technologies, this book is the perfect starting point to begin exploring music generation. The book will help you learn how to use the models in Magenta for generating percussion sequences, monophonic and polyphonic melodies in MIDI, and instrument sounds in raw audio. Through practical examples and in-depth explanations, you’ll understand ML models such as RNNs, VAEs, and GANs. Using this knowledge, you’ll create and train your own models for advanced music generation use cases, along with preparing new datasets. Finally, you’ll get to grips with integrating Magenta with other technologies, such as digital audio workstations (DAWs), and using Magenta.js to distribute music generation apps in the browser. By the end of this book, you'll be well-versed with Magenta and have developed the skills you need to use ML models for music generation in your own style.

Preface

Who this book is for

What this book covers

To get the most out of this book

Code in Action

Get in touch

Section 1: Introduction to Artwork Generation

Free Chapter

Introduction to Magenta and Generative Art

Technical requirements

Overview of generative art

New techniques with machine learning

Google's Magenta and TensorFlow in music generation

Installing Magenta and Magenta for GPU

Installing the music software and synthesizers

Installing the code editing software

Generating a basic MIDI file

Summary

Questions

Further reading

Section 2: Music Generation with Machine Learning

Generating Drum Sequences with the Drums RNN

Technical requirements

The significance of RNNs in music generation

Using the Drums RNN on the command line

Using the Drums RNN in Python

Summary

Questions

Further reading

Generating Polyphonic Melodies

Technical requirements

LSTM for long-term dependencies

Generating melodies with the Melody RNN

Generating polyphony with the Polyphony RNN and Performance RNN

Summary

Questions

Further reading

Latent Space Interpolation with MusicVAE

Technical requirements

Continuous latent space in VAEs

Score transformation with MusicVAE and GrooVAE

Understanding TensorFlow code

Summary

Questions

Further reading

Audio Generation with NSynth and GANSynth

Technical requirements

Learning about WaveNet and temporal structures for music

Neural audio synthesis with NSynth

Using GANSynth as a generative instrument

Summary

Questions

Further reading

Section 3: Training, Learning, and Generating a Specific Style

Data Preparation for Training

Technical requirements

Looking at existing datasets

Building a dance music dataset

Building a jazz dataset

Preparing the data using pipelines

Summary

Questions

Further reading

Training Magenta Models

Technical requirements

Choosing the model and configuration

Training and tuning a model

Using Google Cloud Platform

Summary

Questions

Further reading

Section 4: Making Your Models Interact with Other Applications

Magenta in the Browser with Magenta.js

Technical requirements

Introducing Magenta.js and TensorFlow.js

Creating a Magenta.js web application

Making Magenta.js interact with other apps

Summary

Questions

Further reading

Making Magenta Interact with Music Applications

Technical requirements

Sending MIDI to a DAW or synthesizer

Looping the generated MIDI

Using Magenta as a standalone application with Magenta Studio

Summary

Questions

Technical requirements

In this chapter, we'll use the following tools:

A command line or Bash to launch Magenta from the Terminal
Python and its libraries
The Python multiprocessing module for multi-threaded data preparation
Matplotlib to plot our data preparation results
Magenta to launch data pipeline conversion
MIDI, ABCNotation, and MusicXML as data formats
External APIs such as Last.fm

In Magenta, we'll make use of data pipelines. We will explain these in depth later in this chapter, but if you feel like you need more information, the pipeline README file in Magenta's source code (github.com/tensorflow/magenta/tree/master/magenta/pipelines) is a good place to start. You can also take a look at Magenta's code, which is well documented. There's also additional content in the Further reading section.

The code for this chapter can be found in this book...