EMelodyGen: Emotion-Conditioned Melody Generation in ABC Notation with the Musical Feature Template
This work addresses the challenge of emotion-conditioned music generation for applications in creative AI and music therapy, though it is incremental as it builds on existing methods with new data and templates.
The paper tackles the problem of generating emotional melodies in ABC notation by designing a musical feature template to control emotional expression, achieving 91% alignment with intended emotions in listening tests and a 99% parsing rate for generated melodies.
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.