FAV-DenoiseNet: An Audio–Visual Speech Enhancement Framework Based on Conditional Flow Matching and Visual Encoding

Audio–visual speech enhancement aims to recover clean speech by jointly using noisy acoustic signals and synchronized visual cues. Although diffusion-based methods achieve promising restoration performance, their multi-step sampling causes high inference latency and computational cost, limiting real...

Descrizione completa

Dettagli Bibliografici

Autori principali:	Xuan Fu, Lulu Qin, Weijing Liu, Mingchen Sun, Dadong Wang
Natura:	Artigo
Lingua:	Inglês
Pubblicazione:	MDPI AG 2026-07-01
Serie:	Sensors
Soggetti:	audio–visual speech enhancement conditional flow matching discriminative prior denoising multi-scale cross-modal attention single-step inference
Accesso online:	https://www.mdpi.com/1424-8220/26/13/4175
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!