Speak & Spell: LLM-Driven Controllable Phonetic Error Augmentation for Robust Dialogue State Tracking

Documenti analoghi

• DeRAGEC: Denoising Named Entity Candidates with Synthetic Rationale for ASR Error Correction
  di: Im, Solee, et al.
  Pubblicazione: (2025)
• Inference is All You Need: Self Example Retriever for Cross-domain Dialogue State Tracking with ChatGPT
  di: Lee, Jihyun, et al.
  Pubblicazione: (2024)
• Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech Recognition
  di: Lee, Wonjun, et al.
  Pubblicazione: (2026)
• Acoustic Feature Mixup for Balanced Multi-aspect Pronunciation Assessment
  di: Do, Heejin, et al.
  Pubblicazione: (2024)
• Leveraging What's Overfixed: Post-Correction via LLM Grammatical Error Overcorrection
  di: Park, Taehee, et al.
  Pubblicazione: (2025)