# SURF: Separation via Unsupervised Remixing Flow

arXiv: https://arxiv.org/abs/2606.04921 · HTML: https://mlsanity.com/paper/2606.04921/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 27 of its 47 references that are in the map.
- First posted on arXiv 3 Jun 2026.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 27 of 27)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [Autoencoding beyond pixels using a learned similarity metric](https://mlsanity.com/paper/1512.09300/) (2015)
- [Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation](https://mlsanity.com/paper/1809.07454/) (2018)
- [DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors](https://mlsanity.com/paper/2110.01763/) (2021)
- [LibriMix: An Open-Source Dataset for Generalizable Speech Separation](https://mlsanity.com/paper/2005.11262/) (2020)
- [Multi-Source Diffusion Models for Simultaneous Music Generation and Separation](https://mlsanity.com/paper/2302.02257/) (2023)
- [Learning Diffusion Priors from Observations by Expectation Maximization](https://mlsanity.com/paper/2405.13712/) (2024)
- [Single-Channel Multi-Speaker Separation using Deep Clustering](https://mlsanity.com/paper/1607.02173/) (2016)
- [Diffusion-based Generative Speech Source Separation](https://mlsanity.com/paper/2210.17327/) (2022)
- [Source Separation with Deep Generative Priors](https://mlsanity.com/paper/2002.07942/) (2020)
- [SAM Audio: Segment Anything in Audio](https://mlsanity.com/paper/2512.18099/) (2025)
- [What's All the FUSS About Free Universal Sound Separation Data?](https://mlsanity.com/paper/2011.00803/) (2020)
- [RemixIT: Continual self-training of speech enhancement models via bootstrapped remixing](https://mlsanity.com/paper/2202.08862/) (2022)
- [Generative Adversarial Source Separation](https://mlsanity.com/paper/1710.10779/) (2017)
- [A Mixture-Based Framework for Guiding Diffusion Models](https://mlsanity.com/paper/2502.03332/) (2025)
- [Mel-Band RoFormer for Music Source Separation](https://mlsanity.com/paper/2310.01809/) (2023)
- [TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement](https://mlsanity.com/paper/2408.03440/) (2024)
- [Noise-robust Speech Separation with Fast Generative Correction](https://mlsanity.com/paper/2406.07461/) (2024)
- [Source Separation by Flow Matching](https://mlsanity.com/paper/2505.16119/) (2025)
- [DiffEM: Learning from Corrupted Data with Diffusion Models via Expectation Maximization](https://mlsanity.com/paper/2510.12691/) (2025)
- [Self-Remixing: Unsupervised Speech Separation via Separation and Remixing](https://mlsanity.com/paper/2211.10194/) (2022)
- [EDSep: An Effective Diffusion-Based Method for Speech Source Separation](https://mlsanity.com/paper/2501.15965/) (2025)
- [Unsupervised Single-Channel Audio Separation with Diffusion Source Priors](https://mlsanity.com/paper/2512.07226/) (2025)

## Abstract (arXiv)

The goal of single-channel source separation is to reconstruct K sources given their mixture. In supervised settings where vast amounts of clean source data are available, this challenging, ill-posed problem has been addressed successfully by generative diffusion and flow-based prior models. However, access to such clean source samples is often limited, and even when available, supervised models are vulnerable to domain shifts. To bridge this gap, we present Separation via Unsupervised Remixing Flow (SURF), an unsupervised flow matching approach for source separation that learns directly from observed mixtures. This method relies on a novel combination of state-of-the-art supervised flow matching and regression-based self-supervised techniques. At a high level, starting from a teacher model, we utilize a "remixing" step to bootstrap the learning of a student flow model from the teacher's estimates. We provide insights into the objectives optimized by this approach and draw a novel connection to the Wake-Sleep algorithm. Empirical evaluations on image and audio benchmarks demonstrate that SURF establishes a new state-of-the-art, significantly outperforming existing unsupervised methods. See our demo page for examples. https://google.github.io/df-conformer/surf/