Benchmarking speech-to-text robustness in noisy emergency medical dialogues: an evaluation of models under realistic acoustic conditions
This study introduces a clinically grounded, noise-robust benchmark for STT evaluation in EMS settings. It highlights the importance of domain-specific metrics and acoustic realism for deploying STT systems where transcription errors carry safety-critical consequences.
Authors
- N. Stanic (ORCID: https://orcid.org/0000-0002-8306-0273)
- Murat Sariyar (ORCID: https://orcid.org/0000-0003-3432-2860)
- Denis Moser
Institutions
- University of Bern (CH)
- Bern University of Applied Sciences (CH)
Publication Details
- Journal
- JAMIA Open
- Published
- 2025-11-03
- DOI
- https://doi.org/10.1093/jamiaopen/ooaf147
- Primary Topic
- Speech Recognition and Synthesis
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Science Foundation
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
- Innosuisse - Schweizerische Agentur für Innovationsförderung