MIDI-GPT: A Controllable Generative Model for Computer-Assisted Multitrack Music Composition

TL;DR

MIDI-GPT is a Transformer-based generative model for multitrack music composition that allows controllable, attribute-conditioned infilling and generates stylistically consistent music without copying training data.

Contribution

It introduces a novel musical representation and attribute control mechanisms for Transformer-based music generation, enabling flexible, high-quality composition workflows.

Findings

MIDI-GPT avoids copying training material.

It generates music stylistically similar to training data.

Attribute controls effectively constrain generated music.

Abstract

We present and release MIDI-GPT, a generative system based on the Transformer architecture that is designed for computer-assisted music composition workflows. MIDI-GPT supports the infilling of musical material at the track and bar level, and can condition generation on attributes including: instrument type, musical style, note density, polyphony level, and note duration. In order to integrate these features, we employ an alternative representation for musical material, creating a time-ordered sequence of musical events for each track and concatenating several tracks into a single sequence, rather than using a single time-ordered sequence where the musical events corresponding to different tracks are interleaved. We also propose a variation of our representation allowing for expressiveness. We present experimental results that demonstrate that MIDI-GPT is able to consistently avoid duplicating the musical material it was trained on, generate music that is stylistically similar to the training dataset, and that attribute controls allow enforcing various constraints on the generated material. We also outline several real-world applications of MIDI-GPT, including collaborations with industry partners that explore the integration and evaluation of MIDI-GPT into commercial products, as well as several artistic works produced using it.