Polyffusion: A Diffusion Model for Polyphonic Score Generation with Internal and External Controls

TL;DR

Polyffusion is a diffusion-based model that generates polyphonic music scores with controllability through internal inpainting and external feature conditioning, unifying various music creation tasks.

Contribution

It introduces a novel diffusion model for polyphonic score generation with internal and external controls, enabling versatile music creation tasks.

Findings

Outperforms existing Transformer and sampling-based models

Effective external control with pre-trained representations

Unifies multiple music generation tasks

Abstract

We propose Polyffusion, a diffusion model that generates polyphonic music scores by regarding music as image-like piano roll representations. The model is capable of controllable music generation with two paradigms: internal control and external control. Internal control refers to the process in which users pre-define a part of the music and then let the model infill the rest, similar to the task of masked music generation (or music inpainting). External control conditions the model with external yet related information, such as chord, texture, or other features, via the cross-attention mechanism. We show that by using internal and external controls, Polyffusion unifies a wide range of music creation tasks, including melody generation given accompaniment, accompaniment generation given melody, arbitrary music segment inpainting, and music arrangement given chords or textures. Experimental results show that our model significantly outperforms existing Transformer and sampling-based baselines, and using pre-trained disentangled representations as external conditions yields more effective controls.