A. Kazem

DA-ICL: Distribution-Aware In-Context Learning for Arabic Automatic Speech Recognition Error Correction

A novel two-stage framework for accurate and efficient Arabic ASR enhancement, combining HuBERT-based acoustic modeling with LLM-based DA-ICL correction and LoRA-efficient adaptation yields a robust, accurate, and scalable solution for Arabic ASR, effectively bridging the gap between acoustic signal and linguistic knowledge.