Metraipolis › archive › dc_df42d456f65c
DriftSE: Speech Enhancement with Generative Drifting — arXiv:2609.12252
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.12252
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T03:03:15.929Z
- SHA-256 of the archived text
8b82378cb2b2fd36fe881e6e530c042336e7462efd8a72b885be49365c8ff52f- Stable URL of this page
https://metraipolis.com/documento/dc_df42d456f65c
How to cite
DriftSE: Speech Enhancement with Generative Drifting — arXiv:2609.12252 — arXiv (en), https://arxiv.org/abs/2609.12252 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_df42d456f65c (Metraipolis archive dc_df42d456f65c, sha256 8b82378cb2b2fd36fe881e6e530c042336e7462efd8a72b885be49365c8ff52f)
BibTeX
@misc{dcdf42d456f65c,
title = {DriftSE: Speech Enhancement with Generative Drifting — arXiv:2609.12252},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.12252},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_df42d456f65c; sha256 8b82378cb2b2fd36fe881e6e530c042336e7462efd8a72b885be49365c8ff52f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12252. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 reconstruct the physical signal but risk linguistic hallucination. Therefore, we introduce dual-latent drifting, performing parallel drifting in both semantic and acoustic latents to simultaneously preserve phonetic intelligibility and acoustic fidelity. Additionally, we demonstrate that DriftSE enables fully unpaired training by aligning latent distributions rather than exact point-wise targets. Consequently, DriftSE facilitates cross-dataset learning in the absence of paired noisy-clean samples. Moreover, DriftSE exhibits broad architectural flexibility across different generator backbones. Extensive evaluations on additive denoising and convolutive dereverberation demonstrate robust one-step enhancement across both offline and real-time causal settings. Notably, DriftSE achieves state-of-the-art word error rates across all four evaluated datasets while strictly operating at 1 NFE. Code and audio examples are available online. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI). Categorie arXiv: Sound (cs.SD) ; Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS). Pagina del lavoro: https://arxiv.org/abs/2609.12252 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T02:51:27.885Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).