# Source Separation with Deep Generative Priors

arXiv: https://arxiv.org/abs/2002.07942 · HTML: https://mlsanity.com/paper/2002.07942/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Feb 2020.

## Built on by (most cited first, 30 of 36)

- [Gotta Go Fast When Generating Data with Score-Based Models](https://mlsanity.com/paper/2105.14080/) (2021)
- [Multi-Source Diffusion Models for Simultaneous Music Generation and Separation](https://mlsanity.com/paper/2302.02257/) (2023)
- [Denoising Likelihood Score Matching for Conditional Score-based Data Generation](https://mlsanity.com/paper/2203.14206/) (2022)
- [Diffusion-based Generative Speech Source Separation](https://mlsanity.com/paper/2210.17327/) (2022)
- [Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics](https://mlsanity.com/paper/2105.08164/) (2021)
- [Blind Image Decomposition](https://mlsanity.com/paper/2108.11364/) (2021)
- [Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy](https://mlsanity.com/paper/2211.03796/) (2022)
- [Detector-Free Weakly Supervised Grounding by Separation](https://mlsanity.com/paper/2104.09829/) (2021)
- [Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separation](https://mlsanity.com/paper/2301.10752/) (2023)
- [COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations](https://mlsanity.com/paper/2404.16969/) (2024)
- [Generalized Multi-Source Inference for Text Conditioned Music Diffusion Models](https://mlsanity.com/paper/2403.11706/) (2024)
- [Simultaneous Music Separation and Generation Using Multi-Track Latent Diffusion Models](https://mlsanity.com/paper/2409.12346/) (2024)
- [One-shot Generative Prior in Hankel-k-space for Parallel Imaging Reconstruction](https://mlsanity.com/paper/2208.07181/) (2022)
- [Latent Autoregressive Source Separation](https://mlsanity.com/paper/2301.08562/) (2023)
- [Wavelet Transform-assisted Adaptive Generative Modeling for Colorization](https://mlsanity.com/paper/2107.04261/) (2021)
- [Score-based Source Separation with Applications to Digital Communication Signals](https://mlsanity.com/paper/2306.14411/) (2023)
- [Source Separation by Flow Matching](https://mlsanity.com/paper/2505.16119/) (2025)
- [ArrayDPS: Unsupervised Blind Speech Separation with a Diffusion Prior](https://mlsanity.com/paper/2505.05657/) (2025)
- [MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction](https://mlsanity.com/paper/2505.23305/) (2025)
- [ZeroSep: Separate Anything in Audio with Zero Training](https://mlsanity.com/paper/2505.23625/) (2025)
- [Diffusion-based Signal Refiner for Speech Enhancement and Separation](https://mlsanity.com/paper/2305.05857/) (2023)
- [Unsupervised Single-Channel Audio Separation with Diffusion Source Priors](https://mlsanity.com/paper/2512.07226/) (2025)
- [The Radio-Frequency Transformer for Signal Separation](https://mlsanity.com/paper/2603.09201/) (2026)
- [Unsupervised Source Separation via Bayesian Inference in the Latent Domain](https://mlsanity.com/paper/2110.05313/) (2021)
- [Learning and controlling the source-filter representation of speech with a variational autoencoder](https://mlsanity.com/paper/2204.07075/) (2022)
- [StrADiff: A Structured Source-Wise Adaptive Diffusion Framework for Linear and Nonlinear Blind Source Separation](https://mlsanity.com/paper/2604.04973/) (2026)
- [Blind Source Separation of Single-Channel Mixtures via Multi-Encoder Autoencoders](https://mlsanity.com/paper/2309.07138/) (2023)
- [Weighted-Sum of Gaussian Process Latent Variable Models](https://mlsanity.com/paper/2402.09122/) (2024)
- [Semi-Blind Source Separation with Learned Constraints](https://mlsanity.com/paper/2209.13585/) (2022)
- [Adversarial Generative NMF for Single Channel Source Separation](https://mlsanity.com/paper/2305.01758/) (2023)

## Abstract (arXiv)

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 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 of separation results on CIFAR-10. We also provide qualitative results on LSUN.