AI RESEARCH

Semi-Supervised Diseased Detection from Speech Dialogues with Multi-Level Data Modeling

arXiv CS.AI

ArXi:2601.04744v2 Announce Type: replace-cross Detecting medical conditions from speech acoustics is fundamentally a weakly-supervised learning problem: a single, often noisy, session-level label must be linked to nuanced patterns within a long, complex audio recording. This task is further hampered by severe data scarcity and the subjective nature of clinical annotations.