Score: 1

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

Published: September 18, 2025 | arXiv ID: 2509.14858v2

By: Duojia Li , Shenghui Lu , Hongchen Pan and more

Potential Business Impact:

Cleans up noisy speech in one step.

Business Areas:
Autonomous Vehicles Transportation

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.

Country of Origin
🇨🇳 China

Repos / Data Links

Page Count
5 pages

Category
Computer Science:
Sound