Selective Invocation for Multilingual ASR: A Cost-effective Approach Adapting to Speech Recognition Difficulty

Documenti analoghi

• Enhancing Non-Core Language Instruction-Following in Speech LLMs via Semi-Implicit Cross-Lingual CoT Reasoning
  di: Xue, Hongfei, et al.
  Pubblicazione: (2025)
• Ideal-LLM: Integrating Dual Encoders and Language-Adapted LLM for Multilingual Speech-to-Text
  di: Xue, Hongfei, et al.
  Pubblicazione: (2024)
• dLLM-ASR: A Faster Diffusion LLM-based Framework for Speech Recognition
  di: Tian, Wenjie, et al.
  Pubblicazione: (2026)
• The TEA-ASLP System for Multilingual Conversational Speech Recognition and Speech Diarization in MLC-SLM 2025 Challenge
  di: Xue, Hongfei, et al.
  Pubblicazione: (2025)
• SSHR: Leveraging Self-supervised Hierarchical Representations for Multilingual Automatic Speech Recognition
  di: Xue, Hongfei, et al.
  Pubblicazione: (2023)