论文标题
音乐源分离与生成流
Music Source Separation with Generative Flow
论文作者
论文摘要
用于源分离的完全监督模型在平行混合源数据上进行了训练，目前是最新的。但是，这种并行数据通常很难获得，并且将经过训练的模型适应新来源的混合物很麻烦。相比之下，仅源监督模型只需要单个源数据才能进行培训。在本文中，我们首先利用基于流动的发电机来训练单个音乐源先验，然后将这些模型以及基于可能性的目标以及基于可能性的目标分开音乐混合物。我们表明，在唱歌的语音分离和音乐分离任务中，我们提出的方法具有完全监督的方法。我们还证明，我们可以灵活地添加新型的来源，而完全监督的方法将需要重新训练整个模型。
Fully-supervised models for source separation are trained on parallel mixture-source data and are currently state-of-the-art. However, such parallel data is often difficult to obtain, and it is cumbersome to adapt trained models to mixtures with new sources. Source-only supervised models, in contrast, only require individual source data for training. In this paper, we first leverage flow-based generators to train individual music source priors and then use these models, along with likelihood-based objectives, to separate music mixtures. We show that in singing voice separation and music separation tasks, our proposed method is competitive with a fully-supervised approach. We also demonstrate that we can flexibly add new types of sources, whereas fully-supervised approaches would require retraining of the entire model.
