Symbolic music generation conditioned on continuous-valued emotions
Abstract
In this paper we present a new approach for the generation of multi-instrument symbolic music driven by musical emotion. The principal novelty of our approach centres on conditioning a state-of-the-art transformer based on continuous-valued valence and arousal labels. In addition, we provide a new large-scale dataset of symbolic music paired with emotion labels in terms of valence and arousal. We evaluate our approach in a quantitative manner in two ways, first by measuring its note prediction accuracy, and second via a regression task in the valence-arousal plane. Our results demonstrate that our proposed approaches outperform conditioning using control tokens which is representative of the current state of the art.
Cite
@article{arxiv.2203.16165,
title = {Symbolic music generation conditioned on continuous-valued emotions},
author = {Serkan Sulun and Matthew E. P. Davies and Paula Viana},
journal= {arXiv preprint arXiv:2203.16165},
year = {2022}
}
Comments
Published in IEEE Access