Binbin Zhang

This work presents a multimodal conversational-context framework for LLM-based ASR that integrates a scenario-controlled data pipeline, scalable multimodal context training, and systematic evaluation and introduces MM-ContextASR Bench, which evaluates contextual understanding and entity error correction across five scenarios.

Dialect recognition in ASR can be significantly improved without sacrificing Mandarin accuracy, thanks to a novel self-distillation approach.