Exploring Graph Representation of Chorales

TL;DR

This paper investigates representing Bach chorales as graphs and applying machine learning algorithms to learn node embeddings and labels, revealing salient features for music analysis.

Contribution

It introduces a novel graph-based representation of chorales and applies embedding and classification methods to analyze musical structure.

Findings

Effective node embeddings were learned using CBOW, skip-gram, and node2vec.

Graph-based features captured meaningful musical relationships.

The approach shows promise for music analysis applications.

Abstract

This work explores areas overlapping music, graph theory, and machine learning. An embedding representation of a node, in a weighted undirected graph $\mathcal{G}$, is a representation that captures the meaning of nodes in an embedding space. In this work, 383 Bach chorales were compiled and represented as a graph. Two application cases were investigated in this paper (i) learning node embedding representation using \emph{Continuous Bag of Words (CBOW), skip-gram}, and \emph{node2vec} algorithms, and (ii) learning node labels from neighboring nodes based on a collective classification approach. The results of this exploratory study ascertains many salient features of the graph-based representation approach applicable to music applications.