Boosting Hybrid Autoregressive Transducer-based ASR with Internal Acoustic Model Training and Dual Blank Thresholding

Ähnliche Einträge

• Alignment-Free Training for Transducer-based Multi-Talker ASR
  von: Moriya, Takafumi, et al.
  Veröffentlicht: (2024)
• All-in-One ASR: Unifying Encoder-Decoder Models of CTC, Attention, and Transducer in Dual-Mode ASR
  von: Moriya, Takafumi, et al.
  Veröffentlicht: (2025)
• What Do Self-Supervised Speech and Speaker Models Learn? New Findings From a Cross Model Layer-Wise Analysis
  von: Ashihara, Takanori, et al.
  Veröffentlicht: (2024)
• Generic Speech Enhancement with Self-Supervised Representation Space Loss
  von: Sato, Hiroshi, et al.
  Veröffentlicht: (2025)
• Sentence-wise Speech Summarization: Task, Datasets, and End-to-End Modeling with LM Knowledge Distillation
  von: Matsuura, Kohei, et al.
  Veröffentlicht: (2024)