arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.01049cs.SD
收藏

搜索音乐混音图:一种剪枝方法

Searching For Music Mixing Graphs: A Pruning Approach

Sony AI(索尼人工智能)

Sungho Lee, Marco A. Martínez-Ramírez, Wei-Hsiang Liao, Stefan Uhlich, Giorgio Fabbro, Kyogu Lee, Yuki Mitsufuji

AI总结:

针对从输入输出音频逆向还原音乐混音流程的问题,提出可微调音台参数优化与处理器剪枝交替方法,得到匹配质量接近完整调音台的稀疏混音图。

摘要:

音乐混音具有组合性——专家将多个音频处理器组合起来,从干声音轨获得连贯的混音。我们提出一种从输入和输出音频逆向工程该过程的方法。首先,我们创建一个调音台,将所有可用处理器应用到每条链路上。然后,在初始调音台参数优化之后,我们在移除冗余处理器和微调之间交替进行。我们通过处理器和剪枝的可微实现来实现这一点。因此,我们找到了一个稀疏混音图,其匹配质量与完整调音台几乎相同。我们将此流程应用于来自各种数据集的干声-混音对,并收集同样可用于训练音乐混音应用神经网络的图。

英文摘要:

Music mixing is compositional -- experts combine multiple audio processors to achieve a cohesive mix from dry source tracks. We propose a method to reverse engineer this process from the input and output audio. First, we create a mixing console that applies all available processors to every chain. Then, after the initial console parameter optimization, we alternate between removing redundant processors and fine-tuning. We achieve this through differentiable implementation of both processors and pruning. Consequently, we find a sparse mixing graph that achieves nearly identical matching quality of the full mixing console. We apply this procedure to dry-mix pairs from various datasets and collect graphs that also can be used to train neural networks for music mixing applications.

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。

↑