Papers
arxiv:2509.14858

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

Published on Sep 18
Authors:
,
,
,
,

Abstract

MeanFlowSE is a conditional generative model that uses a Jacobian-vector product to learn average velocity over finite intervals, enabling single-step generation for real-time speech enhancement with lower computational cost.

AI-generated summary

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.

Community

Sign up or log in to comment

Models citing this paper 1

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2509.14858 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2509.14858 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.