音乐源修复挑战赛首次举办，评估了从混音中还原原始乐器音轨的能力。
Summary of The Inaugural Music Source Restoration Challenge
- 基于多指标客观评估与主观评分结合，测试系统恢复能力。
- 冠军系统在多梅尔信噪比上达4.46 dB，主观评分3.47分，领先第二名91%和18%。
- 低频乐器如贝斯恢复效果好，打击乐恢复难度大，仅0.29 dB提升。
音乐源修复（MSR）旨在从专业混音和退化的音频中恢复原始未处理的乐器音轨，需逆转制作效果与真实世界退化。我们举办了首届音乐源修复挑战赛，采用多梅尔信噪比（Multi-Mel-SNR）、Zimtohrli 和 FAD-CLAP 进行客观评估，并对真实退化录音进行主观评价。共有五支团队参与。冠军系统在 Multi-Mel-SNR 上达到 4.46 dB，MOS-Overall 达 3.47，分别较第二名提升 91% 和 18%。逐音轨分析显示，不同乐器恢复难度差异显著，贝斯平均提升 4.59 dB，而打击乐仅 0.29 dB。数据集、评估协议和基线模型已公开于 https://msrchallenge.com/。
原文摘要 · Abstract (English)
Music Source Restoration (MSR) aims to recover original, unprocessed instrument stems from professionally mixed and degraded audio, requiring the reversal of both production effects and real-world degradations. We present the inaugural MSR Challenge, which features objective evaluation on studio-produced mixtures using Multi-Mel-SNR, Zimtohrli, and FAD-CLAP, alongside subjective evaluation on real-world degraded recordings. Five teams participated in the challenge. The winning system achieved 4.46 dB Multi-Mel-SNR and 3.47 MOS-Overall, corresponding to relative improvements of 91% and 18% over the second-place system, respectively. Per-stem analysis reveals substantial variation in restoration difficulty across instruments, with bass averaging 4.59 dB across all teams, while percussion averages only 0.29 dB. The dataset, evaluation protocols, and baselines are available at https://msrchallenge.com/.
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。