aiqbench analysis
This research introduces a novel unpaired speech enhancement framework leveraging Diffusion Schrödinger Bridges and Mamba architectures to address real-world acoustic uncertainty without requiring paired training data. By replacing computationally intensive differential equation simulations with an efficient Mamba-based diffusion model, the approach achieves state-of-the-art performance while significantly accelerating inference speeds for waveform processing. The study demonstrates that this formulation offers robust generalization across diverse speech restoration tasks, advancing the practical deployment of AI-driven audio cleaning systems.
SE-MSB: End-to-End Unpaired Speech Enhancement using Mamba Schr\"odinger Bridges
arXiv:2609.26000v1 Announce Type: cross Abstract: 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 Schr\"odinger 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, usually at each training step. Therefore, we propose using a high-efficiency Mamba Diffusion Model designed for end-to-end waveform processing. We compare against state-of-the-art methods for speech enhancement, both paired and unpaired, as well as a classical signal processing algorithm. Experimental results show that we are on par or better than the baselines while being orders of magnitude faster during inference. Furthermore, we show that the flexibility of the DSB formulation allows our model to generalize across SE tasks, offering a robust and efficient solution for real-world speech restoration.
Abstract: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, usually at each training step. Therefore, we propose using a high-efficiency Mamba Diffusion Model designed for end-to-end waveform processing. We compare against state-of-the-art methods for speech enhancement, both paired and unpaired, as well as a classical signal processing algorithm. Experimental results show that we are on par or better than the baselines while being orders of magnitude faster during inference. Furthermore, we show that the flexibility of the DSB formulation allows our model to generalize across SE tasks, offering a robust and efficient solution for real-world speech restoration.
Audio and Speech Processing (eess.AS); Artificial Intelligence (cs.AI); Sound (cs.SD)
arXiv:2609.26000 [eess.AS]
(or arXiv:2609.26000v1 [eess.AS] for this version)
https://doi.org/10.48550/arXiv.2609.26000 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 268 words
Related coverage
Schr\"odinger Bridge Mamba for One-Step Speech Enhancement
arXiv · Jul 23, 2026
BridgeCodec: Mamba Enhanced Neural Audio Codec with Schr\"odinger Bridge at Low Bitrate
arXiv · Oct 15, 2026
Regularized Schr\"odinger Bridge via Distortion-Perception Perturbation for High-Fidelity Speech Enhancement
arXiv · Aug 4, 2026
Tilted Schr\"odinger Bridge Matching
arXiv · Sep 30, 2026