From Flat Language Labels to Typological Priors: Structured Language Conditioning for Multilingual Speech-to-Speech Translation

Documenti analoghi

• S2ST-Omni: Hierarchical Language-Aware SpeechLLM Adaptation for Multilingual Speech-to-Speech Translation
  di: Pan, Yu, et al.
  Pubblicazione: (2025)
• Assessing the Impact of Typological Features on Multilingual Machine Translation in the Age of Large Language Models
  di: Hirak, Vitalii, et al.
  Pubblicazione: (2026)
• GenTranslate: Large Language Models are Generative Multilingual Speech and Machine Translators
  di: Hu, Yuchen, et al.
  Pubblicazione: (2024)
• Leveraging Unit Language Guidance to Advance Speech Modeling in Textless Speech-to-Speech Translation
  di: Zhang, Yuhao, et al.
  Pubblicazione: (2025)
• Speech-to-Speech Translation Pipelines for Conversations in Low-Resource Languages
  di: Popescu-Belis, Andrei, et al.
  Pubblicazione: (2025)