MOSA: Mixtures of Simple Adapters Outperform Monolithic Approaches in LLM-based Multilingual ASR

Documenti analoghi

• TC-BiMamba: Trans-Chunk bidirectionally within BiMamba for unified streaming and non-streaming ASR
  di: She, Qingshun, et al.
  Pubblicazione: (2026)
• Joint decoding method for controllable contextual speech recognition based on Speech LLM
  di: Fang, Yangui, et al.
  Pubblicazione: (2025)
• Fewer Hallucinations, More Verification: A Three-Stage LLM-Based Framework for ASR Error Correction
  di: Fang, Yangui, et al.
  Pubblicazione: (2025)
• TASU: Text-Only Alignment for Speech Understanding
  di: Peng, Jing, et al.
  Pubblicazione: (2025)
• A Survey on Speech Large Language Models for Understanding
  di: Peng, Jing, et al.
  Pubblicazione: (2024)