The SJTU X-LANCE Lab System for MSR Challenge 2025
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908823358275584 |
|---|---|
| author | Zhu, Jinxuan Qiu, Hao Zhu, Haina Yu, Jianwei Yu, Kai Chen, Xie |
| author_facet | Zhu, Jinxuan Qiu, Hao Zhu, Haina Yu, Jianwei Yu, Kai Chen, Xie |
| contents | This report describes the system submitted to the music source restoration (MSR) Challenge 2025. Our approach is composed of sequential BS-RoFormers, each dealing with a single task including music source separation (MSS), denoise and dereverb. To support 8 instruments given in the task, we utilize pretrained checkpoints from MSS community and finetune the MSS model with several training schemes, including (1) mixing and cleaning of datasets; (2) random mixture of music pieces for data augmentation; (3) scale-up of audio length. Our system achieved the first rank in all three subjective and three objective evaluation metrics, including an MMSNR score of 4.4623 and an FAD score of 0.1988. We have open-sourced all the code and checkpoints at https://github.com/ModistAndrew/xlance-msr. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_09042 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | The SJTU X-LANCE Lab System for MSR Challenge 2025 Zhu, Jinxuan Qiu, Hao Zhu, Haina Yu, Jianwei Yu, Kai Chen, Xie Sound Audio and Speech Processing This report describes the system submitted to the music source restoration (MSR) Challenge 2025. Our approach is composed of sequential BS-RoFormers, each dealing with a single task including music source separation (MSS), denoise and dereverb. To support 8 instruments given in the task, we utilize pretrained checkpoints from MSS community and finetune the MSS model with several training schemes, including (1) mixing and cleaning of datasets; (2) random mixture of music pieces for data augmentation; (3) scale-up of audio length. Our system achieved the first rank in all three subjective and three objective evaluation metrics, including an MMSNR score of 4.4623 and an FAD score of 0.1988. We have open-sourced all the code and checkpoints at https://github.com/ModistAndrew/xlance-msr. |
| title | The SJTU X-LANCE Lab System for MSR Challenge 2025 |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2602.09042 |