Speech-to-SOAP: End-to-End Summarization of Medical Dialogues: KIT@BeTraC 2026
KIT's main contribution is a scalable data augmentation pipeline that unifies heterogeneous medical dialogue datasets through synthetic speech generation and automatically generated SOAP supervision, enabling robust adaptation of a speech foundation model for end-to-end speech-to-SOAP generation.
E. Ugan, Fabian Retkowski, Yuka Ko et al.
· 0 citations