Computer Assisted Composition in Continuous Time

TL;DR

This paper introduces a novel particle filter method for combining symbolic music sequence models with user-defined constraints in continuous time, improving over traditional approaches and producing more agreeable musical compositions.

Contribution

The paper presents a new particle filter approach that generalizes to continuous time and arbitrary rhythm, enhancing music composition models with constraints.

Findings

Particle filter outperforms beam search in statistical properties.

Experimental results show more agreeable music in listening tests.

Method applicable to general continuous time point processes.

Abstract

We address the problem of combining sequence models of symbolic music with user defined constraints. For typical models this is non-trivial as only the conditional distribution of each symbol given the earlier symbols is available, while the constraints correspond to arbitrary times. Previously this has been addressed by assuming a discrete time model of fixed rhythm. We generalise to continuous time and arbitrary rhythm by introducing a simple, novel, and efficient particle filter scheme, applicable to general continuous time point processes. Extensive experimental evaluations demonstrate that in comparison with a more traditional beam search baseline, the particle filter exhibits superior statistical properties and yields more agreeable results in an extensive human listening test experiment.