2 papers
cs.LG2026
Corrective Forcing: Unified Post-Training for Diffusions and Flows in Generative Speech Enhancement
Qing Yao, Lijian Gao, Qirong Mao
Diffusion and flow models, as promising generative paradigms for speech enhancement, face a training--inference mismatch: training uses analytical path states, whereas inference re…
cs.LG2025
Regularized Schrödinger Bridge via Distortion-Perception Perturbation for High-Fidelity Speech Enhancement
Qing Yao, Lijian Gao, Qirong Mao +1
Speech enhancement (SE) requires high-fidelity reconstruction of clean speech that preserves linguistic and paralinguistic cues while maintaining high perceptual quality. Recently,…