FlowSE applies rectified flow matching with a DiT backbone to speech enhancement, reporting better DNSMOS and WER results and a much lower real-time factor than diffusion baselines.
While traditional deterministic methods can attenuate noise, they often struggle to preserve speech naturalness under challenging conditions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.AS 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
FlowSE: Efficient and High-Quality Speech Enhancement via Flow Matching
FlowSE applies rectified flow matching with a DiT backbone to speech enhancement, reporting better DNSMOS and WER results and a much lower real-time factor than diffusion baselines.