GIST Scholar
College of Artificial Intelligence
Department of Electrical Engineering and Computer Science
2. Conference Papers
FlowSE: Flow Matching-based Speech Enhancement
- Type
- Conference Paper
- Citation
- 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025
- Issued Date
- 2025-04-06
- 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. © 2025 IEEE.
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Conference Place
- II
Hyderabad
- Appears in Collections:
- Department of Electrical Engineering and Computer Science > 2. Conference Papers
- 파일 목록
-
-
관련 파일이 존재하지 않습니다.
-
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.