SB-RF: Schrödinger Bridge Rectified Flow for One-Step Robust Speech Enhancement
For speech enhancement practitioners, SB-RF provides a highly efficient one-step generative solution that maintains quality and robustness in challenging real-world conditions.
SB-RF integrates Rectified Flow with Schrödinger Bridge theory to achieve one-step speech enhancement, outperforming other generative methods on the VoiceBank-DEMAND benchmark and showing strong robustness on low-SNR test sets.
Generative models have shown impressive results in speech enhancement but often suffer from multi-step inference. We propose SB-RF, a one-step generative framework integrating Rectified Flow (RF) with Schrödinger Bridge (SB) theory. SB-RF constructs a conditional bridge between clean and noisy speech distributions via entropy-regularized optimal transport. By aligning SB trajectories with the optimal transport geodesic through the velocity-matching objective of RF, SB-RF enables high-quality enhancement with one-step generation. Experiments demonstrate that SB-RF achieves leading performance among generative methods on the VoiceBank-DEMAND benchmark. Furthermore, to fully assess performance in challenging real-world scenarios, we evaluate SB-RF on a simulated low signal-to-noise ratio test set using an expanded training dataset. Under these conditions, SB-RF exhibits strong and competitive robustness with high efficiency, validating its potential for real-world applications.