Motifs, Phrases, and Beyond: The Modelling of Structure in Symbolic Music Generation

TL;DR

This paper reviews the evolution of techniques for modeling musical structure in symbolic music generation, highlighting progress and challenges in capturing motifs, repetitions, and thematic development.

Contribution

It provides a comprehensive overview of symbolic music modeling methods, introduces the concept of sub-task decomposition, and discusses future directions for integrating approaches.

Findings

Progress in capturing motifs and repetitions

Difficulty in modeling nuanced theme development

Emerging use of structural templates and knowledge

Abstract

Modelling musical structure is vital yet challenging for artificial intelligence systems that generate symbolic music compositions. This literature review dissects the evolution of techniques for incorporating coherent structure, from symbolic approaches to foundational and transformative deep learning methods that harness the power of computation and data across a wide variety of training paradigms. In the later stages, we review an emerging technique which we refer to as "sub-task decomposition" that involves decomposing music generation into separate high-level structural planning and content creation stages. Such systems incorporate some form of musical knowledge or neuro-symbolic methods by extracting melodic skeletons or structural templates to guide the generation. Progress is evident in capturing motifs and repetitions across all three eras reviewed, yet modelling the nuanced development of themes across extended compositions in the style of human composers remains difficult. We outline several key future directions to realize the synergistic benefits of combining approaches from all eras examined.