HybridSB-MoE: Dual-Domain Schrödinger Bridges with Scene-Adaptive Expert Routing for Speech Enhancement

• URL: http://arxiv.org/abs/2608.12715v1
• Date: Thu, 13 Aug 2026 02:00:52 GMT
• Title: HybridSB-MoE: Dual-Domain Schrödinger Bridges with Scene-Adaptive Expert Routing for Speech Enhancement
• Abstract summary: HybridSB-MoE is a dual-domain framework for generative speech enhancement.<n>It fills three gaps: spectral models capture harmonic structure but often disrupt phase, waveform models preserve phase but miss harmonics, and Schrdinger Bridges (SB) shorten transport from noise to clean speech but leave cost only loosely tied to training.<n>On VoiceBank+DEMAND, HybridSB-MoE outperforms diffusion- and SB-based baselines at their step budgets.
• Score: 8.444837651455275
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Nonlocality-induced critical-length hierarchy from non-Hermitian competition [48.9823527611878]
  In short-range systems formed by two coupled chains, competition leads to the critical-length law $N_csimln D$.<n>Here we show that long-range hoppings fundamentally reorganizes this critical behavior, producing a hierarchy of distinct scaling laws.<n>Our results offer a platform-independent framework testable in programmable topoelectrical circuits, photonic lattices and digital quantum simulators.
  arXiv  Detail & Related papers  (2026-08-03T18:00:18Z)
• Twisted Schrödinger Bridge Matching [34.126987447337534]
  Diffusion-based Schrdinger bridge models have been proposed to approximate optimal transport dynamics between two prescribed boundary distributions.<n>We introduce Twisted Schrdinger Bridge Matching, a diffusion-based method designed to handle both continuous- and discrete-time potentials.
  arXiv  Detail & Related papers  (2026-07-18T22:30:43Z)
• Attosecond Path Qubits in High-Harmonic Generation: Classical Dephasing and Trace-Out Decoherence [0.0]
  We identify two distinct coherence-loss mechanisms: classical dephasing from ensemble averaging and quantum decoherence arising from the trace-out of unobserved degrees of freedom.<n>These results establish a reduced-state framework for diagnosing coherence loss in HHG and for engineering trajectory-based quantum states in attosecond interferometry.
  arXiv  Detail & Related papers  (2026-06-18T15:35:37Z)
• Coverage Analysis of Rydberg Atom Quantum Receiver Arrays: A Stochastic Geometry Approach [55.47164192369501]
  Rydberg atomic quantum receivers (RAQRs) offer quantum-limited sensitivity and broadband tunability.<n>In dense deployments, aggregate interference can push atomic transducer out of its small-signal regime.<n>This paper addresses the question by embedding the RAQR front end into a geometry coverage analysis.
  arXiv  Detail & Related papers  (2026-05-22T04:05:13Z)
• Inconsistency-aware Multimodal Schrödinger Bridge for Deepfake Localization [11.418398950934671]
  IaMSB is an inconsistency-aware multimodal Schrdinger Bridge.<n>It unifies consistency estimation, cross-modal information selection, and bridge-step scheduling.<n>It stabilizes strict-IoU boundary precision, raising AP@0.95 by 3%10%, and yields improved high-precision localization.
  arXiv  Detail & Related papers  (2026-05-22T00:17:16Z)
• OmniForcing: Unleashing Real-time Joint Audio-Visual Generation [51.031726911410594]
  Recent joint audio-visual diffusion models achieve remarkable generation quality but suffer from high latency.<n>We propose OmniForcing, the first framework to distill an offline, dual-stream bidirectional diffusion model into a high-fidelity streaming autore generator.
  arXiv  Detail & Related papers  (2026-03-12T08:17:36Z)
• Learning to Separate RF Signals Under Uncertainty: Detect-Then-Separate vs. Unified Joint Models [53.79667447811139]
  We show that a single deep neural architecture learns to jointly detect and separate when applied directly to the received signal.<n>These findings highlight UJM as a scalable and practical alternative to DTS, while opening new directions for unified separation under broader estimation.
  arXiv  Detail & Related papers  (2026-02-04T15:25:02Z)
• Topological Residual Asymmetry for Bivariate Causal Direction [1.2691047660244335]
  Topological Residual Asymmetry is a geometry-based criterion for additive-noise models.<n>We quantify a bulk-tube contrast using a 0D persistent-homology functional.<n>Experiments across many challenging synthetic and real-data scenarios demonstrate the method's superiority.
  arXiv  Detail & Related papers  (2026-01-31T00:38:53Z)
• Departures: Distributional Transport for Single-Cell Perturbation Prediction with Neural Schrödinger Bridges [51.83259180910313]
  A major bottleneck in gene function analysis is the unpaired nature of single-cell data.<n>We approximate Schrdinger Bridge (SB) to tackle unpaired single-cell perturbation data.<n>Our model effectively captures heterogeneous single-cell responses and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-11-17T08:27:13Z)
• Analytically Solvable Robust Single-Qubit Gates for Multi-Qubit Systems with Unwanted Couplings [5.169264860833405]
  Couplings between qubits can induce crosstalk errors that degrade single-qubit gate fidelity.<n>We present a novel non-perturbative framework for constructing high-fidelity single-qubit gates in the presence of unwanted couplings.
  arXiv  Detail & Related papers  (2025-03-16T09:33:23Z)
• Noise-resilient Edge Modes on a Chain of Superconducting Qubits [103.93329374521808]
  Inherent symmetry of a quantum system may protect its otherwise fragile states. We implement the one-dimensional kicked Ising model which exhibits non-local Majorana edge modes (MEMs) with $mathbbZ$ parity symmetry. MEMs are found to be resilient against certain symmetry-breaking noise owing to a prethermalization mechanism.
  arXiv  Detail & Related papers  (2022-04-24T22:34:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.