Efficient Fine-Grained Guidance for Diffusion Model Based Symbolic Music Generation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916781503807488 |
|---|---|
| author | Zhu, Tingyu Liu, Haoyu Wang, Ziyu Jiang, Zhimin Zheng, Zeyu |
| author_facet | Zhu, Tingyu Liu, Haoyu Wang, Ziyu Jiang, Zhimin Zheng, Zeyu |
| contents | Developing generative models to create or conditionally create symbolic music presents unique challenges due to the combination of limited data availability and the need for high precision in note pitch. To address these challenges, we introduce an efficient Fine-Grained Guidance (FGG) approach within diffusion models. FGG guides the diffusion models to generate music that aligns more closely with the control and intent of expert composers, which is critical to improve the accuracy, listenability, and quality of generated music. This approach empowers diffusion models to excel in advanced applications such as improvisation, and interactive music creation. We derive theoretical characterizations for both the challenges in symbolic music generation and the effects of the FGG approach. We provide numerical experiments and subjective evaluation to demonstrate the effectiveness of our approach. We have published a demo page to showcase performances, which enables real-time interactive generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_08435 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Efficient Fine-Grained Guidance for Diffusion Model Based Symbolic Music Generation Zhu, Tingyu Liu, Haoyu Wang, Ziyu Jiang, Zhimin Zheng, Zeyu Sound Artificial Intelligence Machine Learning Multimedia Audio and Speech Processing Developing generative models to create or conditionally create symbolic music presents unique challenges due to the combination of limited data availability and the need for high precision in note pitch. To address these challenges, we introduce an efficient Fine-Grained Guidance (FGG) approach within diffusion models. FGG guides the diffusion models to generate music that aligns more closely with the control and intent of expert composers, which is critical to improve the accuracy, listenability, and quality of generated music. This approach empowers diffusion models to excel in advanced applications such as improvisation, and interactive music creation. We derive theoretical characterizations for both the challenges in symbolic music generation and the effects of the FGG approach. We provide numerical experiments and subjective evaluation to demonstrate the effectiveness of our approach. We have published a demo page to showcase performances, which enables real-time interactive generation. |
| title | Efficient Fine-Grained Guidance for Diffusion Model Based Symbolic Music Generation |
| topic | Sound Artificial Intelligence Machine Learning Multimedia Audio and Speech Processing |
| url | https://arxiv.org/abs/2410.08435 |