# EDSep: An Effective Diffusion-Based Method for Speech Source Separation

arXiv: https://arxiv.org/abs/2501.15965 · HTML: https://mlsanity.com/paper/2501.15965/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jan 2025.

## Built on by (most cited first, 5 of 5)

- [Source Separation by Flow Matching](https://mlsanity.com/paper/2505.16119/) (2025)
- [Bayesian Signal Separation via Plug-and-Play Diffusion-Within-Gibbs Sampling](https://mlsanity.com/paper/2509.12857/) (2025)
- [SURF: Separation via Unsupervised Remixing Flow](https://mlsanity.com/paper/2606.04921/) (2026)
- [MeCo: One-Step MeanFlow-based Corrector for Multi-Channel Speech Separation](https://mlsanity.com/paper/2606.09677/) (2026)
- [Generative Learning for Ambisonic Upscaling](https://mlsanity.com/paper/2609.23479/) (2026)

## Abstract (arXiv)

Generative models have attracted considerable attention for speech separation tasks, and among these, diffusion-based methods are being explored. Despite the notable success of diffusion techniques in generation tasks, their adaptation to speech separation has encountered challenges, notably slow convergence and suboptimal separation outcomes. To address these issues and enhance the efficacy of diffusion-based speech separation, we introduce EDSep, a novel single-channel method grounded in score matching via stochastic differential equation (SDE). This method enhances generative modeling for speech source separation by optimizing training and sampling efficiency. Specifically, a novel denoiser function is proposed to approximate data distributions, which obtains ideal denoiser outputs. Additionally, a stochastic sampler is carefully designed to resolve the reverse SDE during the sampling process, gradually separating speech from mixtures. Extensive experiments on databases such as WSJ0-2mix, LRS2-2mix, and VoxCeleb2-2mix demonstrate our proposed method's superior performance over existing diffusion and discriminative models, validating its efficacy.