# Music Source Separation with Generative Flow

arXiv: https://arxiv.org/abs/2204.09079 · HTML: https://mlsanity.com/paper/2204.09079/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2022.

## Built on by (most cited first, 10 of 10)

- [Multi-Source Diffusion Models for Simultaneous Music Generation and Separation](https://mlsanity.com/paper/2302.02257/) (2023)
- [COCOLA: Coherence-Oriented Contrastive Learning of Musical Audio Representations](https://mlsanity.com/paper/2404.16969/) (2024)
- [Simultaneous Music Separation and Generation Using Multi-Track Latent Diffusion Models](https://mlsanity.com/paper/2409.12346/) (2024)
- [MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction](https://mlsanity.com/paper/2505.23305/) (2025)
- [Unsupervised Single-Channel Audio Separation with Diffusion Source Priors](https://mlsanity.com/paper/2512.07226/) (2025)
- [User-guided Generative Source Separation](https://mlsanity.com/paper/2507.01339/) (2025)
- [Efficient and Fast Generative-Based Singing Voice Separation using a Latent Diffusion Model](https://mlsanity.com/paper/2511.20470/) (2025)
- [Improving Music Source Separation with Diffusion and Consistency Refinement](https://mlsanity.com/paper/2412.06965/) (2024)
- [Generating Separated Singing Vocals Using a Diffusion Model Conditioned on Music Mixtures](https://mlsanity.com/paper/2511.21342/) (2025)
- [Unsupervised Single-Channel Speech Separation with Diffusion under Speaker-Embedding Guidance](https://mlsanity.com/paper/2509.24395/) (2025)

## Abstract (arXiv)

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.