SOURCE-LINKED INTELLIGENCE

SE-MSB: End-to-End Unpaired Speech Enhancement using Mamba Schrödinger Bridges

arXiv · AI, language, vision and robotics · article · Sep 22, 2026 · UTC

Speech enhancement (SE) models typically rely on supervised learning with paired data examples where clean speech is synthetically degraded. This paradigm limits performance in real-world scenarios where the target environment's specific acoustic characteristics are unknown. We propose a fully unpaired SE framework that uses principled Diffusion Schrödinger Bridges (DSB) to learn a stochastic transport process between a clean and a degraded speech distribution. Algorithms for learning transport maps are computationally heavy since they require simulating differential equations during training,

Read original source ↗ Open in workspace

recordType

paper

region

Global