AutoSchA: Automatic Hierarchical Music Representations via Multi-Relational Node Isolation

TL;DR

AutoSchA is a novel graph neural network-based framework that automatically generates hierarchical music representations, closely matching expert analysis, thus reducing the manual effort required for music analysis.

Contribution

It introduces a new graph learning and pooling mechanism for hierarchical music analysis, advancing automatic analysis capabilities.

Findings

AutoSchA performs comparably to human experts on Baroque fugue analysis.

The method effectively captures hierarchical musical structures.

It outperforms previous automatic analysis models.

Abstract

Hierarchical representations provide powerful and principled approaches for analyzing many musical genres. Such representations have been broadly studied in music theory, for instance via Schenkerian analysis (SchA). Hierarchical music analyses, however, are highly cost-intensive; the analysis of a single piece of music requires a great deal of time and effort from trained experts. The representation of hierarchical analyses in a computer-readable format is a further challenge. Given recent developments in hierarchical deep learning and increasing quantities of computer-readable data, there is great promise in extending such work for an automatic hierarchical representation framework. This paper thus introduces a novel approach, AutoSchA, which extends recent developments in graph neural networks (GNNs) for hierarchical music analysis. AutoSchA features three key contributions: 1) a new graph learning framework for hierarchical music representation, 2) a new graph pooling mechanism based on node isolation that directly optimizes learned pooling assignments, and 3) a state-of-the-art architecture that integrates such developments for automatic hierarchical music analysis. We show, in a suite of experiments, that AutoSchA performs comparably to human experts when analyzing Baroque fugue subjects.