Emotion-Guided Music Accompaniment Generation Based on Variational Autoencoder

TL;DR

This paper introduces an emotion-guided music accompaniment generation method using a Variational Autoencoder and Valence/Arousal Curve to effectively incorporate human emotions and improve musical structure and richness.

Contribution

It proposes a novel approach combining emotion flow modeling with a Variational Autoencoder and self-attention to enhance emotional expressiveness and structural coherence in AI-generated music accompaniment.

Findings

Improved emotional expressiveness in generated music

Enhanced structural coherence with self-attention

Better interpretability of emotional factors

Abstract

Music accompaniment generation is a crucial aspect in the composition process. Deep neural networks have made significant strides in this field, but it remains a challenge for AI to effectively incorporate human emotions to create beautiful accompaniments. Existing models struggle to effectively characterize human emotions within neural network models while composing music. To address this issue, we propose the use of an easy-to-represent emotion flow model, the Valence/Arousal Curve, which allows for the compatibility of emotional information within the model through data transformation and enhances interpretability of emotional factors by utilizing a Variational Autoencoder as the model structure. Further, we used relative self-attention to maintain the structure of the music at music phrase level and to generate a richer accompaniment when combined with the rules of music theory.