MSRBench：用于音乐源恢复的基准测试数据集
MSRBench: A Benchmarking Dataset for Music Source Restoration
AI总结：
提出首个专为音乐源恢复评估设计的MSRBench基准，包含八类乐器的原始-处理混合对及十二种真实退化，基线实验表明现有模型恢复保真度有待提升。
摘要：
音乐源恢复（MSR）将源分离扩展到现实场景中，信号会经历制作效果（均衡、压缩、混响）和真实世界的退化，目标是恢复原始未处理的源。现有基准无法衡量恢复保真度：合成数据集使用未处理的音轨但混合不现实，而真实制作数据集仅提供已处理的音轨且无干净参考。我们提出了MSRBench，这是首个专为MSR评估设计的基准。MSRBench包含八种乐器类别的原始音轨-混合对，混合由专业混音工程师制作。这些原始-处理对能够直接评估分离准确性和恢复保真度。除了受控录音室条件，混合还增加了十二种真实世界退化，涵盖模拟伪影、声学环境和有损编解码器。使用U-Net和BSRNN的基线实验分别实现-37.8 dB和-23.4 dB的SI-SNR，感知质量（FAD CLAP）约为0.7-0.8，表明仍有大幅改进空间，需要专为恢复设计的架构。
英文摘要：
Music Source Restoration (MSR) extends source separation to realistic settings where signals undergo production effects (equalization, compression, reverb) and real-world degradations, with the goal of recovering the original unprocessed sources. Existing benchmarks cannot measure restoration fidelity: synthetic datasets use unprocessed stems but unrealistic mixtures, while real production datasets provide only already-processed stems without clean references. We present MSRBench, the first benchmark explicitly designed for MSR evaluation. MSRBench contains raw stem-mixture pairs across eight instrument classes, where mixtures are produced by professional mixing engineers. These raw-processed pairs enable direct evaluation of both separation accuracy and restoration fidelity. Beyond controlled studio conditions, the mixtures are augmented with twelve real-world degradations spanning analog artifacts, acoustic environments, and lossy codecs. Baseline experiments with U-Net and BSRNN achieve SI-SNR of -37.8 dB and -23.4 dB respectively, with perceptual quality (FAD CLAP) around 0.7-0.8, demonstrating substantial room for improvement and the need for restoration-specific architectures.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
