Symbolic Music Generation with Fine-grained Interactive Textural Guidance
Zhu, Tingyu, Liu, Haoyu, Jiang, Zhimin, Zheng, Zeyu
–arXiv.org Artificial Intelligence
The problem of symbolic music generation presents unique challenges due to the combination of limited data availability and the need for high precision in note pitch. To overcome these difficulties, we introduce Fine-grained Textural Guidance (FTG) within diffusion models to correct errors in the learned distributions. By incorporating FTG, the diffusion models improve the accuracy of music generation, which makes them well-suited for advanced tasks such as progressive music generation, improvisation and interactive music creation. We derive theoretical characterizations for both the challenges in symbolic music generation and the effect of the FTG approach. We provide numerical experiments and a demo page for interactive music generation with user input to showcase the effectiveness of our approach.
arXiv.org Artificial Intelligence
Oct-10-2024
- Genre:
- Research Report > New Finding (0.46)
- Industry:
- Leisure & Entertainment (1.00)
- Media > Music (1.00)
- Technology: