Reducing Prompt Sensitivity in LLM-based Speech Recognition Through Learnable Projection

Documenti analoghi

• Text-only adaptation in LLM-based ASR through text denoising
  di: Carofilis, Andrés, et al.
  Pubblicazione: (2026)
• TokenVerse++: Towards Flexible Multitask Learning with Dynamic Task Activation
  di: Kumar, Shashi, et al.
  Pubblicazione: (2025)
• Better Semi-supervised Learning for Multi-domain ASR Through Incremental Retraining and Data Filtering
  di: Carofilis, Andres, et al.
  Pubblicazione: (2025)
• Unifying Global and Near-Context Biasing in a Single Trie Pass
  di: Thorbecke, Iuliia, et al.
  Pubblicazione: (2024)
• Efficient Data Selection for Domain Adaptation of ASR Using Pseudo-Labels and Multi-Stage Filtering
  di: Rangappa, Pradeep, et al.
  Pubblicazione: (2025)