DeepBach: a Steerable Model for Bach Chorales Generation

TL;DR

DeepBach is a steerable graphical model trained on Bach chorales that can generate convincing polyphonic music and allows user constraints, with an accessible plugin for music editing.

Contribution

It introduces a novel graphical model for polyphonic music generation that is steerable and integrates with existing music editing tools.

Findings

Generates highly convincing Bach-style chorales

Allows user constraints during music generation

Provides an easy-to-use MuseScore plugin

Abstract

This paper introduces DeepBach, a graphical model aimed at modeling polyphonic music and specifically hymn-like pieces. We claim that, after being trained on the chorale harmonizations by Johann Sebastian Bach, our model is capable of generating highly convincing chorales in the style of Bach. DeepBach's strength comes from the use of pseudo-Gibbs sampling coupled with an adapted representation of musical data. This is in contrast with many automatic music composition approaches which tend to compose music sequentially. Our model is also steerable in the sense that a user can constrain the generation by imposing positional constraints such as notes, rhythms or cadences in the generated score. We also provide a plugin on top of the MuseScore music editor making the interaction with DeepBach easy to use.