Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.00576 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917301967650816 |
|---|---|
| author | Xu, Jinhan Tang, Xing Yang, Houpeng Zhang, Haoran Yuan, Shenghua Chen, Jiatao Xi, Tianming Wang, Jing Yu, Jiaojiao Xiang, Guangli |
| author_facet | Xu, Jinhan Tang, Xing Yang, Houpeng Zhang, Haoran Yuan, Shenghua Chen, Jiatao Xi, Tianming Wang, Jing Yu, Jiaojiao Xiang, Guangli |
| contents | Symbolic music generation is a challenging task in multimedia generation, involving long sequences with hierarchical temporal structures, long-range dependencies, and fine-grained local details. Though recent diffusion-based models produce high quality generations, they tend to suffer from high training and inference costs with long symbolic sequences due to iterative denoising and sequence-length-related costs. To deal with such problem, we put forth a diffusing strategy named SMDIM to combine efficient global structure construction and light local refinement. SMDIM uses structured state space models to capture long range musical context at near linear cost, and selectively refines local musical details via a hybrid refinement scheme. Experiments performed on a wide range of symbolic music datasets which encompass various Western classical music, popular music and traditional folk music show that the SMDIM model outperforms the other state-of-the-art approaches on both the generation quality and the computational efficiency, and it has robust generalization to underexplored musical styles. These results show that SMDIM offers a principled solution for long-sequence symbolic music generation, including associated attributes that accompany the sequences. We provide a project webpage with audio examples and supplementary materials at https://3328702107.github.io/smdim-music/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_00576 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Efficient Long-Sequence Diffusion Modeling for Symbolic Music Generation Xu, Jinhan Tang, Xing Yang, Houpeng Zhang, Haoran Yuan, Shenghua Chen, Jiatao Xi, Tianming Wang, Jing Yu, Jiaojiao Xiang, Guangli Sound Artificial Intelligence Symbolic music generation is a challenging task in multimedia generation, involving long sequences with hierarchical temporal structures, long-range dependencies, and fine-grained local details. Though recent diffusion-based models produce high quality generations, they tend to suffer from high training and inference costs with long symbolic sequences due to iterative denoising and sequence-length-related costs. To deal with such problem, we put forth a diffusing strategy named SMDIM to combine efficient global structure construction and light local refinement. SMDIM uses structured state space models to capture long range musical context at near linear cost, and selectively refines local musical details via a hybrid refinement scheme. Experiments performed on a wide range of symbolic music datasets which encompass various Western classical music, popular music and traditional folk music show that the SMDIM model outperforms the other state-of-the-art approaches on both the generation quality and the computational efficiency, and it has robust generalization to underexplored musical styles. These results show that SMDIM offers a principled solution for long-sequence symbolic music generation, including associated attributes that accompany the sequences. We provide a project webpage with audio examples and supplementary materials at https://3328702107.github.io/smdim-music/. |
| title | Efficient Long-Sequence Diffusion Modeling for Symbolic Music Generation |
| topic | Sound Artificial Intelligence |
| url | https://arxiv.org/abs/2603.00576 |