REMAST: Real-time Emotion-based Music Arrangement with Soft Transition

TL;DR

REMAST is a real-time music arrangement system that dynamically adapts to changing emotions, ensuring both emotional fit and smooth transitions by fusing past and current emotional cues and leveraging domain knowledge features.

Contribution

The paper introduces REMAST, a novel system that balances emotion real-time fit with smooth transitions in music generation using emotion fusion, feature enhancement, and semi-supervised learning.

Findings

REMAST outperforms existing methods in objective metrics.

REMAST achieves superior subjective evaluation scores.

The system maintains emotional coherence with real-time adaptation.

Abstract

Music as an emotional intervention medium has important applications in scenarios such as music therapy, games, and movies. However, music needs real-time arrangement according to changing emotions, bringing challenges to balance emotion real-time fit and soft emotion transition due to the fine-grained and mutable nature of the target emotion. Existing studies mainly focus on achieving emotion real-time fit, while the issue of smooth transition remains understudied, affecting the overall emotional coherence of the music. In this paper, we propose REMAST to address this trade-off. Specifically, we recognize the last timestep's music emotion and fuse it with the current timestep's input emotion. The fused emotion then guides REMAST to generate the music based on the input melody. To adjust music similarity and emotion real-time fit flexibly, we downsample the original melody and feed it into the generation model. Furthermore, we design four music theory features by domain knowledge to enhance emotion information and employ semi-supervised learning to mitigate the subjective bias introduced by manual dataset annotation. According to the evaluation results, REMAST surpasses the state-of-the-art methods in objective and subjective metrics. These results demonstrate that REMAST achieves real-time fit and smooth transition simultaneously, enhancing the coherence of the generated music.