Saved in:
Bibliographic Details
Main Authors: Wang, Jiahe, Wang, Hongyu, Wang, Wei, Yang, Lei, Li, Chenda, Zhang, Wangyou, Tan, Lufen, Qian, Yanmin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.21214
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Speech enhancement (SE) improves degraded speech's quality, with generative models like flow matching gaining attention for their outstanding perceptual quality. However, the flow-based model requires multiple numbers of function evaluations (NFEs) to achieve stable and satisfactory performance, leading to high computational load and poor 1-NFE performance. In this paper, we propose MeanSE, an efficient generative speech enhancement model using mean flows, which models the average velocity field to achieve high-quality 1-NFE enhancement. Experimental results demonstrate that our proposed MeanSE significantly outperforms the flow matching baseline with a single NFE, exhibiting extremely better out-of-domain generalization capabilities.