Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Jiahe, Wang, Hongyu, Wang, Wei, Yang, Lei, Li, Chenda, Zhang, Wangyou, Tan, Lufen, Qian, Yanmin
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2509.21214
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909805993525248
author Wang, Jiahe
Wang, Hongyu
Wang, Wei
Yang, Lei
Li, Chenda
Zhang, Wangyou
Tan, Lufen
Qian, Yanmin
author_facet Wang, Jiahe
Wang, Hongyu
Wang, Wei
Yang, Lei
Li, Chenda
Zhang, Wangyou
Tan, Lufen
Qian, Yanmin
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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21214
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MeanSE: Efficient Generative Speech Enhancement with Mean Flows
Wang, Jiahe
Wang, Hongyu
Wang, Wei
Yang, Lei
Li, Chenda
Zhang, Wangyou
Tan, Lufen
Qian, Yanmin
Audio and Speech Processing
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.
title MeanSE: Efficient Generative Speech Enhancement with Mean Flows
topic Audio and Speech Processing
url https://arxiv.org/abs/2509.21214