@InProceedings{Mühlhausen2025_1238,
<br/>   author = {Sara Mühlhausen and Sarah Gomez and Norina Lauer and Timo Baumann},
<br/>   booktitle = {Studientexte zur Sprachkommunikation: Elektronische Sprachsignalverarbeitung 2025},
<br/>   title = {Cross lingual transfer learning does not improve aphasic speech recognition},
<br/>   year = {2025},
<br/>   editor = {Sven Grawunder},
<br/>   month = mar,
<br/>   pages = {77--84},
<br/>   publisher = {TUDpress, Dresden},
<br/>   abstract  = {In addressing the particular linguistic challenges posed by patients suffering from aphasia, a language disorder, this paper proposes a fine-tuning approach
to enhance the speech recognition capabilities of existing models. The available
aphasic research data in German is highly limited. To address this constraint, we
propose a cross-lingual transfer approach to utilize English data to improve performance in German. This advancement aims to support the development of a
therapy platform tailored for patients with aphasia. For the base speech recognition
model, we choose to use OpenAI’s Whisper model, and for fine-tuning, we make
use of TalkBank’s AphasiaBank. The experimental findings demonstrate that the
transcription of aphasic audio with Whisper is less successful than non-aphasic
audio. However, fine-tuning the transcription in the respective language resulted in
an enhancement of its quality. In contrast, fine-tuning the transcription in another
language and expecting a transfer of the learned aphasic speech properties led to a
deterioration in its quality.
},
<br/>   isbn = {978-3-95908-803-9},
<br/>   issn = {0940-6832},
<br/>   keywords = {Recognition in HMI and Therapeutic Applications},
<br/>   url = {https://www.essv.de/pdf/2025_77_84.pdf},
<br/>}