SynesLM: A Unified Approach for Audio-visual Speech Recognition and Translation via Language Model and Synthetic Data

Documenti analoghi

• Robust Audiovisual Speech Recognition Models with Mixture-of-Experts
  di: Wu, Yihan, et al.
  Pubblicazione: (2024)
• TMT: Tri-Modal Translation between Speech, Image, and Text by Processing Different Modalities as Different Languages
  di: Kim, Minsu, et al.
  Pubblicazione: (2024)
• Towards Robust Speech Representation Learning for Thousands of Languages
  di: Chen, William, et al.
  Pubblicazione: (2024)
• SpeechComposer: Unifying Multiple Speech Tasks with Prompt Composition
  di: Wu, Yihan, et al.
  Pubblicazione: (2024)
• SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation Leveraging NLP Evaluation Metrics
  di: Saeki, Takaaki, et al.
  Pubblicazione: (2024)