Emotion-driven Piano Music Generation via Two-stage Disentanglement and Functional Representation
This work addresses the problem of inadequate emotional modeling in music generation for applications in creative AI, though it appears incremental as it builds on prior disentanglement approaches with specific enhancements.
The paper tackles the challenge of modeling emotions in automatic piano music generation by proposing a two-stage framework that disentangles valence and arousal, introducing a novel functional representation to capture emotional features like tonality and note interactions. Objective and subjective experiments validate the framework's effectiveness in emotional modeling, and it is applied to emotional controls for music generation.
Managing the emotional aspect remains a challenge in automatic music generation. Prior works aim to learn various emotions at once, leading to inadequate modeling. This paper explores the disentanglement of emotions in piano performance generation through a two-stage framework. The first stage focuses on valence modeling of lead sheet, and the second stage addresses arousal modeling by introducing performance-level attributes. To further capture features that shape valence, an aspect less explored by previous approaches, we introduce a novel functional representation of symbolic music. This representation aims to capture the emotional impact of major-minor tonality, as well as the interactions among notes, chords, and key signatures. Objective and subjective experiments validate the effectiveness of our framework in both emotional valence and arousal modeling. We further leverage our framework in a novel application of emotional controls, showing a broad potential in emotion-driven music generation.