TMT: Tri-Modal Translation between Speech, Image, and Text by Processing Different Modalities as Different Languages

Documenti analoghi

• Voxtlm: unified decoder-only models for consolidating speech recognition/synthesis and speech/text continuation tasks
  di: Maiti, Soumi, et al.
  Pubblicazione: (2023)
• SynesLM: A Unified Approach for Audio-visual Speech Recognition and Translation via Language Model and Synthetic Data
  di: Lu, Yichen, et al.
  Pubblicazione: (2024)
• Efficient Training for Multilingual Visual Speech Recognition: Pre-training with Discretized Visual Speech Representation
  di: Kim, Minsu, et al.
  Pubblicazione: (2024)
• OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer
  di: Peng, Yifan, et al.
  Pubblicazione: (2024)
• Scheduled Interleaved Speech-Text Training for Speech-to-Speech Translation with LLMs
  di: Futami, Hayato, et al.
  Pubblicazione: (2025)