基于分步处理的音频修复系统，在音乐源分离任务中表现最佳。
The SJTU X-LANCE Lab System for MSR Challenge 2025
- 分阶段使用BS-RoFormers处理分离、降噪与去混响任务
- 在三项主观与六项客观指标上排名第一，MMSNR达4.4623
- 适合对音频修复与音乐信号处理感兴趣的开发者
本文介绍提交至音乐源恢复（MSR）挑战赛2025的系统。该方法采用一系列顺序执行的BS-RoFormers，分别处理音乐源分离（MSS）、降噪和去混响任务。为支持任务中提出的8种乐器，我们利用音乐源分离社区的预训练权重，并通过三种训练策略进行微调：（1）数据集混合与清洗；（2）随机混合乐曲进行数据增强；（3）音频长度扩展。系统在所有三项主观评价与三项客观评价指标上均排名第一，其中MMSNR得分为4.4623，FAD得分为0.1988。相关代码与模型检查点已开源，地址为https://github.com/ModistAndrew/xlance-msr。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。