基于逐样本增益反转的音乐去限制器网络
Music De-limiter Networks via Sample-wise Gain Inversion
AI总结：
针对音乐行业响度战争导致音乐动态范围受损的问题，提出基于逐样本增益反转的音乐去限制器网络，搭配构建的musdb-XL-train数据集训练，在重建任务中取得24.0 dB的SI-SDR优异性能。
摘要：
响度战争是音乐行业中一种持续存在的现象，其特征是音乐最终响度不断提升而动态范围不断缩小，数十年来一直是颇具争议的话题。音乐母带工程师使用限制器对音乐进行重度压缩以提升响度，这可能会导致听众产生听觉疲劳甚至听力损失。本文提出了音乐去限制器网络，可从重度压缩的信号中估计出未压缩的音乐。受限制器对给定信号执行逐样本增益降低的原理启发，我们提出了逐样本增益反转（SGI）框架。我们还构建了musdb-XL-train数据集，该数据集包含30万个片段，通过应用商业限制器插件生成，用于训练适配真实场景的去限制器网络。我们提出的去限制器网络取得了优异的性能：在从musdb-XL数据（即施加了限制器的musdb-HQ版本）重建musdb-HQ的任务中，尺度不变源失真比（SI-SDR）达到24.0 dB。训练数据、代码和模型权重可在我们的代码库（https://github.com/jeonchangbin49/De-limiter）中获取。
英文摘要：
The loudness war, an ongoing phenomenon in the music industry characterized by the increasing final loudness of music while reducing its dynamic range, has been a controversial topic for decades. Music mastering engineers have used limiters to heavily compress and make music louder, which can induce ear fatigue and hearing loss in listeners. In this paper, we introduce music de-limiter networks that estimate uncompressed music from heavily compressed signals. Inspired by the principle of a limiter, which performs sample-wise gain reduction of a given signal, we propose the framework of sample-wise gain inversion (SGI). We also present the musdb-XL-train dataset, consisting of 300k segments created by applying a commercial limiter plug-in for training real-world friendly de-limiter networks. Our proposed de-limiter network achieves excellent performance with a scale-invariant source-to-distortion ratio (SI-SDR) of 24.0 dB in reconstructing musdb-HQ from musdb-XL data, a limiter-applied version of musdb-HQ. The training data, codes, and model weights are available in our repository (https://github.com/jeonchangbin49/De-limiter).
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。
