EMelodyGen: Emotion-Conditioned Melody Generation in ABC Notation with the Musical Feature Template

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Monan, Li, Xiaobing, Yu, Feng, Li, Wei
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915290387841024
author Zhou, Monan
Li, Xiaobing
Yu, Feng
Li, Wei
author_facet Zhou, Monan
Li, Xiaobing
Yu, Feng
Li, Wei
contents The EMelodyGen system focuses on emotional melody generation in ABC notation controlled by the musical feature template. Owing to the scarcity of well-structured and emotionally labeled sheet music, we designed a template for controlling emotional melody generation by statistical correlations between musical features and emotion labels derived from small-scale emotional symbolic music datasets and music psychology conclusions. We then automatically annotated a large, well-structured sheet music collection with rough emotional labels by the template, converted them into ABC notation, and reduced label imbalance by data augmentation, resulting in a dataset named Rough4Q. Our system backbone pre-trained on Rough4Q can achieve up to 99% music21 parsing rate and melodies generated by our template can lead to a 91% alignment on emotional expressions in blind listening tests. Ablation studies further validated the effectiveness of the feature controls in the template. Available code and demos are at https://github.com/monetjoe/EMelodyGen.
format Preprint
id arxiv_https___arxiv_org_abs_2309_13259
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle EMelodyGen: Emotion-Conditioned Melody Generation in ABC Notation with the Musical Feature Template
Zhou, Monan
Li, Xiaobing
Yu, Feng
Li, Wei
Information Retrieval
Artificial Intelligence
Sound
Audio and Speech Processing
The EMelodyGen system focuses on emotional melody generation in ABC notation controlled by the musical feature template. Owing to the scarcity of well-structured and emotionally labeled sheet music, we designed a template for controlling emotional melody generation by statistical correlations between musical features and emotion labels derived from small-scale emotional symbolic music datasets and music psychology conclusions. We then automatically annotated a large, well-structured sheet music collection with rough emotional labels by the template, converted them into ABC notation, and reduced label imbalance by data augmentation, resulting in a dataset named Rough4Q. Our system backbone pre-trained on Rough4Q can achieve up to 99% music21 parsing rate and melodies generated by our template can lead to a 91% alignment on emotional expressions in blind listening tests. Ablation studies further validated the effectiveness of the feature controls in the template. Available code and demos are at https://github.com/monetjoe/EMelodyGen.
title EMelodyGen: Emotion-Conditioned Melody Generation in ABC Notation with the Musical Feature Template
topic Information Retrieval
Artificial Intelligence
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2309.13259