Categorize Early, Integrate Late: Divergent Processing Strategies in Automatic Speech Recognition

Documenti analoghi

• In-Context Learning Boosts Speech Recognition via Human-like Adaptation to Speakers and Language Varieties
  di: Roll, Nathan, et al.
  Pubblicazione: (2025)
• PSST! Prosodic Speech Segmentation with Transformers
  di: Roll, Nathan, et al.
  Pubblicazione: (2023)
• Transcribe, Translate, or Transliterate: An Investigation of Intermediate Representations in Spoken Language Models
  di: Ògúnrèmí, Tolúlopé, et al.
  Pubblicazione: (2025)
• CTC-DRO: Robust Optimization for Reducing Language Disparities in Speech Recognition
  di: Bartelds, Martijn, et al.
  Pubblicazione: (2025)
• False Friends Are Not Foes: Investigating Vocabulary Overlap in Multilingual Language Models
  di: Kallini, Julie, et al.
  Pubblicazione: (2025)