Improving Zero-Shot Chinese-English Code-Switching ASR with kNN-CTC and Gated Monolingual Datastores

Documenti analoghi

• kNN-CTC: Enhancing ASR via Retrieval of CTC Pseudo Labels
  di: Zhou, Jiaming, et al.
  Pubblicazione: (2023)
• Iterative Prototype Refinement for Ambiguous Speech Emotion Recognition
  di: Sun, Haoqin, et al.
  Pubblicazione: (2024)
• Speaker-Smoothed kNN Speaker Adaptation for End-to-End ASR
  di: Li, Shaojun, et al.
  Pubblicazione: (2024)
• Enhancing Multimodal Emotion Recognition through Multi-Granularity Cross-Modal Alignment
  di: Wang, Xuechen, et al.
  Pubblicazione: (2024)
• Uncertainty-Aware Mean Opinion Score Prediction
  di: Wang, Hui, et al.
  Pubblicazione: (2024)