MedSpeak: A Knowledge Graph-Aided ASR Error Correction Framework for Spoken Medical QA

ArXi:2602.00981v2 Announce Type: replace-cross Spoken question-answering (SQA) systems relying on automatic speech recognition (ASR) often struggle with accurately recognizing medical terminology. To this end, we propose MedSpeak, a novel knowledge graph-aided ASR error correction framework that refines noisy transcripts and improves downstream answer prediction by leveraging both semantic relationships and phonetic information encoded in a medical knowledge graph, together with the reasoning power of LLMs.