Metraipolis › archive › dc_99210cda1bf6
HybridSB-MoE: Dual-Domain Schrödinger Bridges with Scene-Adaptive Expert Routing for Speech Enhancement — arXiv:2608.12715
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.12715
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:18:04.894Z
- SHA-256 of the archived text
3cf3f8a8be164c5d7eb376f973d9904c7ed9c8f194a7a0a70320aaf7501a62b4- Stable URL of this page
https://metraipolis.com/documento/dc_99210cda1bf6
How to cite
HybridSB-MoE: Dual-Domain Schrödinger Bridges with Scene-Adaptive Expert Routing for Speech Enhancement — arXiv:2608.12715 — arXiv (en), https://arxiv.org/abs/2608.12715 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_99210cda1bf6 (Metraipolis archive dc_99210cda1bf6, sha256 3cf3f8a8be164c5d7eb376f973d9904c7ed9c8f194a7a0a70320aaf7501a62b4)
BibTeX
@misc{dc99210cda1bf6,
title = {HybridSB-MoE: Dual-Domain Schrödinger Bridges with Scene-Adaptive Expert Routing for Speech Enhancement — arXiv:2608.12715},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.12715},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_99210cda1bf6; sha256 3cf3f8a8be164c5d7eb376f973d9904c7ed9c8f194a7a0a70320aaf7501a62b4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12715. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generative speech enhancement faces three gaps: spectral models capture harmonic structure but often disrupt phase, waveform models preserve phase but miss harmonics, and Schrödinger Bridges (SB) shorten transport from noise to clean speech but leave inference cost only loosely tied to training. We propose HybridSB-MoE, a dual-domain framework that fills these gaps through three contributions unified by a single asymmetric design principle. (i) Asymmetric uncertainty fusion: The spectral path captures epistemic uncertainty via expert disagreement, while the waveform bridge models aleatoric variance through stochastic dynamics. We fuse them asymmetrically, allowing the mixing weight to adapt to distinct error regimes rather than average predictions. (ii) Heterogeneous MoE with top-k=2 routing across five distinct architectural archetypes, where architectural diversity makes the epistemic signal indicate which inductive bias fails rather than small perturbations among similar experts. (iii) Discretization bound (Theorem 1): path-consistency and trajectory regularizers together bound the K-step bridge sampling error in 2-Wasserstein distance at rate K-alpha, making small-K inference an objective-level guarantee rather than an empirical claim. On VoiceBank+DEMAND, HybridSB-MoE outperforms diffusion- and SB-based baselines at their step budgets while remaining competitive with consistency-distilled few-step methods. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.AI). Categorie arXiv: Sound (cs.SD) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.12715 — 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 2026-10-19T04:13:06.693Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).