Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Emotion-Driven Melody Harmonization via Melodic Variation and Functional Representation

Jingyue Huang, Yi-Hsuan Yang

TL;DR

Experimental results confirm the effectiveness of the novel functional representation for symbolic music in generating key-aware harmonies, and objective and subjective evaluations affirming the potential of the approach to convey specific valence for versatile melody.

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 results confirm the effectiveness of our new representation in generating key-aware harmonies, with objective and subjective evaluations affirming the potential of our approach to convey specific valence for versatile melody.

Emotion-Driven Melody Harmonization via Melodic Variation and Functional Representation

TL;DR

Experimental results confirm the effectiveness of the novel functional representation for symbolic music in generating key-aware harmonies, and objective and subjective evaluations affirming the potential of the approach to convey specific valence for versatile melody.

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 results confirm the effectiveness of our new representation in generating key-aware harmonies, with objective and subjective evaluations affirming the potential of our approach to convey specific valence for versatile melody.
Paper Structure (10 sections, 5 figures, 3 tables)

This paper contains 10 sections, 5 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Method
  4. Functional Representation
  5. Model Architecture
  6. Experiments
  7. Datasets, Preprocessing, and Model Settings
  8. Objective Evaluation
  9. User Study
  10. Conclusion and Future Work

Figures (5)

  • Figure 1: Key histogram of high/low valence clips from EMOPIA emopia.
  • Figure 2: Illustration of (a) REMI remi and (b) the proposed functional representation, differing in note pitch and chord name events.
  • Figure 3: Illustration of the conversion between letters and Roman numerals in the cases of C major / c minor. The solid line represents a direct one-to-one conversion, while the dotted line stands for a random conversion to either one of them.
  • Figure 4: Examples of functional representations for two bars, featuring solely emotion, key, note pitches, and chords for simplification.
  • Figure 5: Comparison of subjective results under different settings.