Are Transformers in Pre-trained LM A Good ASR Encoder? An Empirical Study

Documenti analoghi

• Loss Masking Is Not Needed in Decoder-only Transformer for Discrete-token-based ASR
  di: Chen, Qian, et al.
  Pubblicazione: (2023)
• Bridging Speech and Text: Enhancing ASR with Pinyin-to-Character Pre-training in LLMs
  di: Yuhang, Yang, et al.
  Pubblicazione: (2024)
• Unifying Diarization, Separation, and ASR with Multi-Speaker Encoder
  di: Shakeel, Muhammad, et al.
  Pubblicazione: (2025)
• Enhancing the Robustness of Contextual ASR to Varying Biasing Information Volumes Through Purified Semantic Correlation Joint Modeling
  di: Gu, Yue, et al.
  Pubblicazione: (2025)
• Performance Analysis of Speech Encoders for Low-Resource SLU and ASR in Tunisian Dialect
  di: Mdhaffar, Salima, et al.
  Pubblicazione: (2024)