Steer-by-prior Editing of Symbolic Music Loops

TL;DR

This paper introduces Superposed Language Modelling, a novel approach for controllable symbolic music loop editing that incorporates priors over sequences, enabling flexible constraints during generation and editing of MIDI loops.

Contribution

It presents a new Superposed Language Model for symbolic music, allowing constraint-based editing and generation, advancing controllable music synthesis methods.

Findings

Effective in various MIDI loop editing tasks

Demonstrates flexible constraint application during inference

Highlights limitations and future directions

Abstract

With the goal of building a system capable of controllable symbolic music loop generation and editing, this paper explores a generalisation of Masked Language Modelling we call Superposed Language Modelling. Rather than input tokens being known or unknown, a Superposed Language Model takes priors over the sequence as input, enabling us to apply various constraints to the generation at inference time. After detailing our approach, we demonstrate our model across various editing tasks in the domain of multi-instrument MIDI loops. We end by highlighting some limitations of the approach and avenues for future work. We provides examples from the SLM across multiple generation and editing tasks at https://erl-j.github.io/slm-mml-demo/.