AAAI 2026technical0 citations

PASE: Leveraging the Phonological Prior of WavLM for Low-Hallucination Generative Speech Enhancement

Xiaobin Rong, Qinwen Hu, Mansur Yesilbursa, Kamil Wojcicki, Jing Lu

Abstract

Generative models have shown remarkable performance in speech enhancement (SE), achieving superior perceptual quality over traditional discriminative approaches. However, existing generative SE approaches often overlook the risk of hallucination under severe noise, leading to incorrect spoken content or inconsistent speaker characteristics, which we term linguistic and acoustic hallucinations, respectively. We argue that linguistic hallucination stems from models

BibTeX
@inproceedings{aaai2026_paseleveragingth,
  title = {PASE: Leveraging the Phonological Prior of WavLM for Low-Hallucination Generative Speech Enhancement},
  author = {Xiaobin Rong and Qinwen Hu and Mansur Yesilbursa and Kamil Wojcicki and Jing Lu},
  booktitle = {AAAI 2026},
  year = {2026}
}