Emotion-Driven Melody Harmonization via Melodic Variation and Functional Representation
Jingyue Huang, Yi-Hsuan Yang

TL;DR
This paper introduces a novel functional music representation and a Transformer-based model for emotion-driven melody harmonization, enabling key-aware and varied harmonies to better convey specific emotions in melodies.
Contribution
It proposes a new symbolic music representation considering keys and melodic variation, improving emotion modeling and harmony diversity in melody harmonization.
Findings
Effective in generating key-aware harmonies
Improves emotional valence conveyance
Validated by objective and subjective evaluations
Abstract
Emotion-driven melody harmonization aims to generate diverse harmonies for a single melody to convey desired emotions. Previous research found it hard to alter the perceived emotional valence of lead sheets only by harmonizing the same melody with different chords, which may be attributed to the constraints imposed by the melody itself and the limitation of existing music representation. In this paper, we propose a novel functional representation for symbolic music. This new method takes musical keys into account, recognizing their significant role in shaping music's emotional character through major-minor tonality. It also allows for melodic variation with respect to keys and addresses the problem of data scarcity for better emotion modeling. A Transformer is employed to harmonize key-adaptable melodies, allowing for keys determined in rule-based or model-based manner. Experimental…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMusic and Audio Processing · Music Technology and Sound Studies · Speech and Audio Processing
MethodsAttention Is All You Need · Label Smoothing · Adam · Linear Layer · Byte Pair Encoding · Layer Normalization · Softmax · Position-Wise Feed-Forward Layer · Dense Connections · Multi-Head Attention
