Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition

Documenti analoghi

• Pseudo2Real: Task Arithmetic for Pseudo-Label Correction in Automatic Speech Recognition
  di: Lin, Yi-Cheng, et al.
  Pubblicazione: (2025)
• SMILE: Speech Meta In-Context Learning for Low-Resource Language Automatic Speech Recognition
  di: Hsu, Ming-Hao, et al.
  Pubblicazione: (2024)
• Fusion of Discrete Representations and Self-Augmented Representations for Multilingual Automatic Speech Recognition
  di: Wang, Shih-heng, et al.
  Pubblicazione: (2024)
• Continual Test-time Adaptation for End-to-end Speech Recognition on Noisy Speech
  di: Lin, Guan-Ting, et al.
  Pubblicazione: (2024)
• Mitigating Subgroup Disparities in Multi-Label Speech Emotion Recognition: A Pseudo-Labeling and Unsupervised Learning Approach
  di: Lin, Yi-Cheng, et al.
  Pubblicazione: (2025)