Documenti analoghi

• Making Acoustic Side-Channel Attacks on Noisy Keyboards Viable with LLM-Assisted Spectrograms' "Typo" Correction
  di: Ayati, Seyyed Ali, et al.
  Pubblicazione: (2025)
• FastAdaSP: Multitask-Adapted Efficient Inference for Large Speech Language Model
  di: Lu, Yichen, et al.
  Pubblicazione: (2024)
• SPBA: Utilizing Speech Large Language Model for Backdoor Attacks on Speech Classification Models
  di: Yao, Wenhan, et al.
  Pubblicazione: (2025)
• MUGEN: Evaluating and Improving Multi-audio Understanding of Large Audio-Language Models
  di: Yang, Chih-Kai, et al.
  Pubblicazione: (2026)
• It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition
  di: Chen, Chen, et al.
  Pubblicazione: (2024)