@InProceedings{Foysal2026_1274,
<br/>   author = {Abdullah Al Foysal and Ronald Böck},
<br/>   booktitle = {Studientexte zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2026, Tagungsband der 37. Konferenz},
<br/>   title = {Enhancing ASR for German Medical Domain without Fine-Tuning},
<br/>   year = {2026},
<br/>   editor = {Günther Wirsching},
<br/>   month = mar,
<br/>   pages = {24--31},
<br/>   publisher = {TUDpress, Dresden},
<br/>   abstract  = {Speech recognition in medical context is important but also challenging. Especially the
adaptation of speech models is a concern directly influencing the performance of models and thus, the application of such technology in medical working processes. This issue is related to the availability of speech samples for fine-tuning the systems, which is often problematic to regulatory aspects. Since, however, speech processing provides benefits for medical personnel to optimise working processes, we propose a pipeline, allowing adaption of speech processing as well as automatic output formatting. We decided to establish a post-processing approach, using pre-trained (not necessarily medically updated) speech models, being combined with lexicon- and processing techniques to allow adaptation to medical technical terms. Furthermore, the pipeline comprises handling of spoken formatting commands. The entire system is working (close to) real-time. In the paper, we also demonstrate our approach in a first study.},
<br/>   isbn = {978-3-95908-834-3},
<br/>   issn = {0940-6832},
<br/>   keywords = {Speech Signal Recognition and Enhancement},
<br/>   url = {https://www.essv.de/pdf/2026_24_31.pdf},
<br/>}