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.

翻译：完全受监督的源分离模式在平行混合源数据方面受过培训,目前是最先进的。然而,这种平行数据往往难以获得,而且将经过培训的模型适应新来源的混合物十分繁琐。相比之下,只有来源监督的模式只要求培训个别源数据。在本文中,我们首先利用流动生成器来培训单个音乐源前科,然后利用这些模型以及基于可能性的目标,将音乐混合物分开。我们表明,在唱语音分离和音乐分离的任务中,我们提出的方法具有竞争力,采用完全监督的方法。我们还表明,我们可以灵活地增加新的源,而完全监督的方法则需要对整个模式进行再培训。