SOURCE-LINKED INTELLIGENCE

Bridging the Modality Gap in Long-Form Clinical Audio: A Comparative Study of Lightweight and Heavyweight End-to-End SOAP Generation

arXiv · AI, language, vision and robotics · article · Sep 13, 2026 · UTC

Automating clinical documentation from long-form doctor-patient conversations remains challenging for modern audio-language models. While cascaded ASR systems perform well, end-to-end (E2E) models often struggle with information loss and hallucinations on extended audio. For the BeTraC 2026 challenge, the ASLP team presents a fully E2E multimodal system that generates structured SOAP notes directly from audio, bypassing intermediate transcripts. We constructed a 1.41-million-sample multi-task corpus and applied a multi-stage pipeline: domain pre-training, supervised fine-tuning, and reward opt

Read original source ↗ Open in workspace

recordType

paper

region

Global