EchoX: Towards Mitigating Acoustic-Semantic Gap via Echo Training for Speech-to-Speech LLMs

Documenti analoghi

• Leveraging Unit Language Guidance to Advance Speech Modeling in Textless Speech-to-Speech Translation
  di: Zhang, Yuhao, et al.
  Pubblicazione: (2025)
• Soundwave: Less is More for Speech-Text Alignment in LLMs
  di: Zhang, Yuhao, et al.
  Pubblicazione: (2025)
• Roadmap towards Superhuman Speech Understanding using Large Language Models
  di: Bu, Fan, et al.
  Pubblicazione: (2024)
• Ti-Audio: The First Multi-Dialectal End-to-End Speech LLM for Tibetan
  di: Wang, Jialing, et al.
  Pubblicazione: (2026)
• MTalk-Bench: Evaluating Speech-to-Speech Models in Multi-Turn Dialogues via Arena-style and Rubrics Protocols
  di: Du, Yuhao, et al.
  Pubblicazione: (2025)