Combinatorial music generation model with song structure graph analysis

TL;DR

This paper introduces a novel symbolic music generation approach using a song structure graph analysis network, leveraging graph neural networks and U-Net to produce comprehensive musical compositions.

Contribution

It presents a new graph-based model that integrates note sequences and instrument information for improved symbolic music generation.

Findings

Model can generate comprehensive music forms

Graph neural network effectively captures song structure

Potential applications in music composition and classification

Abstract

In this work, we propose a symbolic music generation model with the song structure graph analysis network. We construct a graph that uses information such as note sequence and instrument as node features, while the correlation between note sequences acts as the edge feature. We trained a Graph Neural Network to obtain node representation in the graph, then we use node representation as input of Unet to generate CONLON pianoroll image latent. The outcomes of our experimental results show that the proposed model can generate a comprehensive form of music. Our approach represents a promising and innovative method for symbolic music generation and holds potential applications in various fields in Music Information Retreival, including music composition, music classification, and music inpainting systems.