REINA: Regularized Entropy Information-Based Loss for Efficient Simultaneous Speech Translation

Documenti analoghi

• Regularized Entropy Information Adaptation with Temporal-Awareness Networks for Simultaneous Speech Translation
  di: Liu, Joseph, et al.
  Pubblicazione: (2026)
• Diffusion Synthesizer for Efficient Multilingual Speech to Speech Translation
  di: Hirschkind, Nameer, et al.
  Pubblicazione: (2024)
• Enhancing Multilingual Voice Toxicity Detection with Speech-Text Alignment
  di: Liu, Joseph, et al.
  Pubblicazione: (2024)
• SimulTron: On-Device Simultaneous Speech to Speech Translation
  di: Agranovich, Alex, et al.
  Pubblicazione: (2024)
• AlignAtt: Using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translation
  di: Papi, Sara, et al.
  Pubblicazione: (2023)