Metraipolis › archive › dc_f1832f08cdad
Corrective Forcing: Unified Post-Training for Diffusions and Flows in Generative Speech Enhancement — arXiv:2609.24651
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.24651
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T07:07:53.312Z
- SHA-256 of the archived text
234d4c28ab2d182a65af338e10d3c19b15b6b2348eae8eafb670ecbc56aa9352- Stable URL of this page
https://metraipolis.com/documento/dc_f1832f08cdad
How to cite
Corrective Forcing: Unified Post-Training for Diffusions and Flows in Generative Speech Enhancement — arXiv:2609.24651 — arXiv (en), https://arxiv.org/abs/2609.24651 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f1832f08cdad (Metraipolis archive dc_f1832f08cdad, sha256 234d4c28ab2d182a65af338e10d3c19b15b6b2348eae8eafb670ecbc56aa9352)
BibTeX
@misc{dcf1832f08cdad,
title = {Corrective Forcing: Unified Post-Training for Diffusions and Flows in Generative Speech Enhancement — arXiv:2609.24651},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.24651},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f1832f08cdad; sha256 234d4c28ab2d182a65af338e10d3c19b15b6b2348eae8eafb670ecbc56aa9352},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24651. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 toward the ground truth under dynamic sampling schedules, exposing the model to varying inference conditions. It further regularizes local evolution using locally corrected counterfactual transitions as references for factual transitions. By expressing model outputs through a shared clean-speech prediction parameterization, CoF applies the same post-training objective across diffusion and flow formulations. Experiments with SB-VE and OT-CFM demonstrate improvements in perceptual quality and reconstruction fidelity, together with robust performance across different numbers of sampling steps. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.24651 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-09T06:58:09.439Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).