SOURCE-LINKED INTELLIGENCE

DriftSE: Speech Enhancement with Generative Drifting

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

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 the generator's pushforward distribution with the clean speech manifold through drifting in a latent domain. During inference, the drifting process is discarded, enabling one-step generation. We establish that its enhancement quality depends fundamentally on the choice of latent representation. Semantic latents preserve phonetic structure but fail to capture physical acoustic cues, whereas acoustic latents reconstru

Read original source ↗ Open in workspace

recordType

paper

region

Global