Learning Interpretable Musical Compositional Rules and Traces

TL;DR

This paper introduces MUS-ROVER, a system that automatically learns interpretable musical rules from symbolic data, mimicking a music theorist’s approach to understanding compositional patterns.

Contribution

MUS-ROVER is a novel self-learning system that uses n-gram models to discover and analyze musical rules from symbolic music data, including known and new patterns.

Findings

Successfully recovers known musical rules from Bach chorales

Identifies new characteristic compositional patterns

Demonstrates potential for aiding human and machine composition

Abstract

Throughout music history, theorists have identified and documented interpretable rules that capture the decisions of composers. This paper asks, "Can a machine behave like a music theorist?" It presents MUS-ROVER, a self-learning system for automatically discovering rules from symbolic music. MUS-ROVER performs feature learning via $n$-gram models to extract compositional rules --- statistical patterns over the resulting features. We evaluate MUS-ROVER on Bach's (SATB) chorales, demonstrating that it can recover known rules, as well as identify new, characteristic patterns for further study. We discuss how the extracted rules can be used in both machine and human composition.