Reducing Linguistic Hallucination in LM-Based Speech Enhancement via Noise-Invariant Acoustic-Semantic Distillation

Documenti analoghi

• PASE: Leveraging the Phonological Prior of WavLM for Low-Hallucination Generative Speech Enhancement
  di: Rong, Xiaobin, et al.
  Pubblicazione: (2025)
• Thinking in cocktail party: Chain-of-Thought and reinforcement learning for target speaker automatic speech recognition
  di: Zhang, Yiru, et al.
  Pubblicazione: (2025)
• Lightweight speech enhancement guided target speech extraction in noisy multi-speaker scenarios
  di: Huang, Ziling, et al.
  Pubblicazione: (2025)
• StuPASE: Towards Low-Hallucination Studio-Quality Generative Speech Enhancement
  di: Rong, Xiaobin, et al.
  Pubblicazione: (2026)
• UniPASE: A Generative Model for Universal Speech Enhancement with High Fidelity and Low Hallucinations
  di: Rong, Xiaobin, et al.
  Pubblicazione: (2026)