Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs

Documenti analoghi

• NIM4-ASR: Towards Efficient, Robust, and Customizable Real-Time LLM-Based ASR
  di: Xie, Yuan, et al.
  Pubblicazione: (2026)
• Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition
  di: Bai, Ye, et al.
  Pubblicazione: (2024)
• dLLM-ASR: A Faster Diffusion LLM-based Framework for Speech Recognition
  di: Tian, Wenjie, et al.
  Pubblicazione: (2026)
• FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM Integration
  di: Xu, Kai-Tuo, 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)