Showing cs.SDShow all
3 papers · 1 filter
cs.SD2026
Unsupervised Speech Enhancement via Drifting
Diego Caviedes-Nozal, Liang Xu, Rasmus Kongsgaard Olsson +1
This paper addresses unsupervised speech enhancement in the unpaired setting using drifting methods, where training relies on separate collections of degraded and clean audio witho…
cs.SD2026
DriftSE: Speech Enhancement with Generative Drifting
Liang Xu, Diego Caviedes-Nozal, W. Bastiaan Kleijn +2
We propose DriftSE, a novel one-step generative framework for speech enhancement formulated as a latent distribution equilibrium problem. During training, the drifting field aligns…
cs.SD2026
Speech Enhancement Based on Drifting Models
Liang Xu, Diego Caviedes-Nozal, W. Bastiaan Kleijn +2
We propose Speech Enhancement based on Drifting Models (DriftSE), a novel generative framework that formulates denoising as an equilibrium problem. Rather than relying on iterative…