SpeechMedAssist: Efficiently and Effectively Adapting Speech Language Models for Medical Consultation

ArXi:2601.04638v2 Announce Type: replace Medical consultations are intrinsically speech-centric. However, most prior works focus on long-text-based interactions, which are cumbersome and patient-unfriendly. Recent advances in speech language models (SpeechLMs) have enabled natural speech-based interaction, yet the scarcity of medical speech data and the inefficiency of directly fine-tuning on speech data jointly hinder the adoption of SpeechLMs in medical consultation.