FNSE-SBGAN: Far-field Speech Enhancement With Schrodinger Bridge And Generative Adversarial Networks

Abstract

The prevailing method for neural speech enhancement predominantly utilizes fully-supervised deep learning with simulated pairs of far-field noisy-reverberant speech and clean speech. Nonetheless, these models frequently demonstrate restricted generalizability to mixtures recorded in real-world conditions. To address this issue, this study investigates training enhancement models directly on real mixtures. Specifically, we revisit the single-channel far-field to near-field speech enhancement (FNSE) task, focusing on real-world data characterized by low signal-to-noise ratio (SNR), high reverberation, and mid-to-high frequency attenuation. We propose FNSE-SBGAN, a framework that integrates a Schrodinger Bridge (SB)-based diffusion model with generative adversarial networks (GANs). Our approach achieves state-of-the-art performance across various metrics and subjective evaluations, significantly reducing the character error rate (CER) by up to 14.58% compared to far-field signals. Experim

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keylei2025fnse

Related papers

• Diffusion-based Speech Enhancement With Schr\"odinger Bridge And Symmetric Noise Schedule (2024)0.00
• SEGAN: Speech Enhancement Generative Adversarial Network (2017)21.85
• Robust Speech Recognition With Schr\"odinger Bridge-based Speech Enhancement (2025)2.26
• SEFGAN: Harvesting The Power Of Normalizing Flows And Gans For Efficient High-quality Speech Enhancement (2023)5.84
• Investigating Training Objectives For Generative Speech Enhancement (2024)9.76
• Towards Generalized Speech Enhancement With Generative Adversarial Networks (2019)10.35
• Conditional Generative Adversarial Networks For Speech Enhancement And Noise-robust Speaker Verification (2017)16.03
• Single Channel Far Field Feature Enhancement For Speaker Verification In The Wild (2020)0.00