English

FlowSE: Flow Matching-based Speech Enhancement

Audio and Speech Processing 2025-08-12 v1 Signal Processing

Abstract

Diffusion probabilistic models have shown impressive performance for speech enhancement, but they typically require 25 to 60 function evaluations in the inference phase, resulting in heavy computational complexity. Recently, a fine-tuning method was proposed to correct the reverse process, which significantly lowered the number of function evaluations (NFE). Flow matching is a method to train continuous normalizing flows which model probability paths from known distributions to unknown distributions including those described by diffusion processes. In this paper, we propose a speech enhancement based on conditional flow matching. The proposed method achieved the performance comparable to those for the diffusion-based speech enhancement with the NFE of 60 when the NFE was 5, and showed similar performance with the diffusion model correcting the reverse process at the same NFE from 1 to 5 without additional fine tuning procedure. We also have shown that the corresponding diffusion model derived from the conditional probability path with a modified optimal transport conditional vector field demonstrated similar performances with the NFE of 5 without any fine-tuning procedure.

Keywords

Cite

@article{arxiv.2508.06840,
  title  = {FlowSE: Flow Matching-based Speech Enhancement},
  author = {Seonggyu Lee and Sein Cheong and Sangwook Han and Jong Won Shin},
  journal= {arXiv preprint arXiv:2508.06840},
  year   = {2025}
}

Comments

Published in ICASSP 2025

R2 v1 2026-07-01T04:42:15.474Z