SOURCE-LINKED INTELLIGENCE

Corrective Forcing: Unified Post-Training for Diffusions and Flows in Generative Speech Enhancement

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

Diffusion and flow models, as promising generative paradigms for speech enhancement, face a training--inference mismatch: training uses analytical path states, whereas inference recursively evaluates models on self-generated rollout states along discretized sampling trajectories. This mismatch causes prediction and discretization errors to accumulate. To address it, we introduce Corrective Forcing (CoF), a post-training paradigm that forces diffusion and flow models to learn from self-generated rollouts and correct their predictions. CoF corrects clean-speech predictions on rollout states towa

Read original source ↗ Open in workspace

recordType

paper

region

Global