English

MeanFlowSE: one-step generative speech enhancement via conditional mean flow

Sound 2026-03-05 v3 Artificial Intelligence

Abstract

Multistep inference is a bottleneck for real-time generative speech enhancement because flow- and diffusion-based systems learn an instantaneous velocity field and therefore rely on iterative ordinary differential equation (ODE) solvers. We introduce MeanFlowSE, a conditional generative model that learns the average velocity over finite intervals along a trajectory. Using a Jacobian-vector product (JVP) to instantiate the MeanFlow identity, we derive a local training objective that directly supervises finite-interval displacement while remaining consistent with the instantaneous-field constraint on the diagonal. At inference, MeanFlowSE performs single-step generation via a backward-in-time displacement, removing the need for multistep solvers; an optional few-step variant offers additional refinement. On VoiceBank-DEMAND, the single-step model achieves strong intelligibility, fidelity, and perceptual quality with substantially lower computational cost than multistep baselines. The method requires no knowledge distillation or external teachers, providing an efficient, high-fidelity framework for real-time generative speech enhancement. The proposed method is open-sourced at https://github.com/liduojia1/MeanFlowSE.

Keywords

Cite

@article{arxiv.2509.14858,
  title  = {MeanFlowSE: one-step generative speech enhancement via conditional mean flow},
  author = {Duojia Li and Shenghui Lu and Hongchen Pan and Zongyi Zhan and Qingyang Hong and Lin Li},
  journal= {arXiv preprint arXiv:2509.14858},
  year   = {2026}
}
R2 v1 2026-07-01T05:43:39.050Z