Source Separation with Deep Generative Priors

Vivek Jayaram · John Thickstun

Keywords: [ Bayesian Methods ] [ Deep Generative Models ] [ Deep Learning - Generative Models and Autoencoders ]

[ Abstract ] [ Join Zoom
Please do not share or post zoom links


Despite substantial progress in signal source separation, results for richly structured data continue to contain perceptible artifacts. In contrast, recent deep generative models can produce authentic samples in a variety of domains that are indistinguishable from samples of the data distribution. This paper introduces a Bayesian approach to source separation that uses deep generative models as priors over the components of a mixture of sources, and noise-annealed Langevin dynamics to sample from the posterior distribution of sources given a mixture. This decouples the source separation problem from generative modeling, enabling us to directly use cutting-edge generative models as priors. The method achieves state-of-the-art performance for MNIST digit separation. We introduce new methodology for evaluating separation quality on richer datasets, providing quantitative evaluation and qualitative discussion of results for CIFAR-10 image separation.

Chat is not available.