Structure-Enhanced Pop Music Generation via Harmony-Aware Learning

TL;DR

This paper introduces a harmony-aware learning approach and a hierarchical transformer model to improve the structural quality of automatically generated pop music, focusing on texture and form coherence.

Contribution

It proposes a novel harmony-aware hierarchical transformer that jointly learns texture and form, enhancing pop music generation quality and structural understanding.

Findings

HAT outperforms existing methods in structure understanding.

Generated music shows improved form and texture coherence.

Experimental results demonstrate better musical quality and structure.

Abstract

Pop music generation has always been an attractive topic for both musicians and scientists for a long time. However, automatically composing pop music with a satisfactory structure is still a challenging issue. In this paper, we propose to leverage harmony-aware learning for structure-enhanced pop music generation. On the one hand, one of the participants of harmony, chord, represents the harmonic set of multiple notes, which is integrated closely with the spatial structure of music, the texture. On the other hand, the other participant of harmony, chord progression, usually accompanies the development of the music, which promotes the temporal structure of music, the form. Moreover, when chords evolve into chord progression, the texture and form can be bridged by the harmony naturally, which contributes to the joint learning of the two structures. Furthermore, we propose the Harmony-Aware Hierarchical Music Transformer (HAT), which can exploit the structure adaptively from the music, and make the musical tokens interact hierarchically to enhance the structure in multi-level musical elements. Experimental results reveal that compared to the existing methods, HAT owns a much better understanding of the structure and it can also improve the quality of generated music, especially in the form and texture.