Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs

Documenti analoghi

• Decoder-only Architecture for Speech Recognition with CTC Prompts and Text Data Augmentation
  di: Tsunoo, Emiru, et al.
  Pubblicazione: (2023)
• Hypothesis Clustering and Merging: Novel MultiTalker Speech Recognition with Speaker Tokens
  di: Kashiwagi, Yosuke, et al.
  Pubblicazione: (2024)
• Spiralformer: Low Latency Encoder for Streaming Speech Recognition with Circular Layer Skipping and Early Exiting
  di: Tsunoo, Emiru, et al.
  Pubblicazione: (2025)
• Rapid Language Adaptation for Multilingual E2E Speech Recognition Using Encoder Prompting
  di: Kashiwagi, Yosuke, et al.
  Pubblicazione: (2024)
• Decoder-only Architecture for Streaming End-to-end Speech Recognition
  di: Tsunoo, Emiru, et al.
  Pubblicazione: (2024)