Advanced Modeling of Interlanguage Speech Intelligibility Benefit with L1-L2 Multi-Task Learning Using Differentiable K-Means for Accent-Robust Discrete Token-Based ASR

Documents similaires

• Discrete Tokens Exhibit Interlanguage Speech Intelligibility Benefit: an Analytical Study Towards Accent-robust ASR Only with Native Speech Data
  par: Onda, Kentaro, et autres
  Publié: (2025)
• Prosodically Enhanced Foreign Accent Simulation by Discrete Token-based Resynthesis Only with Native Speech Corpora
  par: Onda, Kentaro, et autres
  Publié: (2025)
• Benchmarking Prosody Encoding in Discrete Speech Tokens
  par: Onda, Kentaro, et autres
  Publié: (2025)
• A Pilot Study of GSLM-based Simulation of Foreign Accentuation Only Using Native Speech Corpora
  par: Onda, Kentaro, et autres
  Publié: (2024)
• A Perception-Based L2 Speech Intelligibility Indicator: Leveraging a Rater's Shadowing and Sequence-to-sequence Voice Conversion
  par: Geng, Haopeng, et autres
  Publié: (2025)