Perception-Inspired Graph Convolution for Music Understanding Tasks

TL;DR

This paper introduces MusGConv, a perception-inspired graph convolutional block tailored for musical score analysis, improving performance across various music understanding tasks by incorporating fundamental perceptual principles.

Contribution

The paper presents MusGConv, a novel graph convolutional block that models pitch and rhythm based on perceptual principles, enhancing musical score processing.

Findings

Improves performance on three music understanding tasks

Efficient and conceptually simple design

Highlights importance of perception-informed processing

Abstract

We propose a new graph convolutional block, called MusGConv, specifically designed for the efficient processing of musical score data and motivated by general perceptual principles. It focuses on two fundamental dimensions of music, pitch and rhythm, and considers both relative and absolute representations of these components. We evaluate our approach on four different musical understanding problems: monophonic voice separation, harmonic analysis, cadence detection, and composer identification which, in abstract terms, translate to different graph learning problems, namely, node classification, link prediction, and graph classification. Our experiments demonstrate that MusGConv improves the performance on three of the aforementioned tasks while being conceptually very simple and efficient. We interpret this as evidence that it is beneficial to include perception-informed processing of fundamental musical concepts when developing graph network applications on musical score data.