Accent related errors in clinical speech transcription and a LLM-based remedy

Fatapour, Yasaman; S. Samaan, Jamil; P. Tatonetti, Nicholas; Kuchi, Aditi; Srinivasan, Apoorva; Fatapour, Sarvenaz; Liu, Hongyu; Berkowitz, Jacob; K. Tsang, Kevin; Ziets, Michael; A. Friedrich, Nadine; Srinivasan, Nitin; Thangaratnam, Shehan; C King, Ryan; Czarny, Ryan; Nguyen, Trini; Hui Yeo, Yee; Hyunseok, Kim; Lee, Yi‐Te; Wongjarupong, Nicha; Abiri, Arash

doi:10.1038/s41746-026-02490-z

Public

Accent related errors in clinical speech transcription and a LLM-based remedy

Published in npj Digital Medicine • Mar 2, 2026

Authors:

Yasaman Fatapour

Jamil S. Samaan

Nicholas P. Tatonetti

Abstract

Accurate clinical documentation is essential for safe, effective patient care. AI tools powered by automatic speech recognition can streamline this process. Variable performance across speakers with diverse accents leads to transcription errors and clinical risk. In testing Whisper and WhisperX on n...

Subject

Transcription (linguistics)

Speech recognition

Stress (linguistics)

Research Assistant

AI chat, annotations, notes & similar papers

Finding related papers...

Discussions

(0)

No comments yet

Be the first to share your thoughts!