Uncovering the Potential for a Weakly Supervised End-to-End Model in Recognising Speech from Patient with Post-Stroke Aphasia

Giulia Sanguedolce, Patrick A. Naylor, Fatemeh Geranmayeh


Abstract
Post-stroke speech and language deficits (aphasia) significantly impact patients’ quality of life. Many with mild symptoms remain undiagnosed, and the majority do not receive the intensive doses of therapy recommended, due to healthcare costs and/or inadequate services. Automatic Speech Recognition (ASR) may help overcome these difficulties by improving diagnostic rates and providing feedback during tailored therapy. However, its performance is often unsatisfactory due to the high variability in speech errors and scarcity of training datasets. This study assessed the performance of Whisper, a recently released end-to-end model, in patients with post-stroke aphasia (PWA). We tuned its hyperparameters to achieve the lowest word error rate (WER) on aphasic speech. WER was significantly higher in PWA compared to age-matched controls (10.3% vs 38.5%, p<0.001). We demonstrated that worse WER was related to the more severe aphasia as measured by expressive (overt naming, and spontaneous speech production) and receptive (written and spoken comprehension) language assessments. Stroke lesion size did not affect the performance of Whisper. Linear mixed models accounting for demographic factors, therapy duration, and time since stroke, confirmed worse Whisper performance with left hemispheric frontal lesions.We discuss the implications of these findings for how future ASR can be improved in PWA.
Anthology ID:
2023.clinicalnlp-1.24
Volume:
Proceedings of the 5th Clinical Natural Language Processing Workshop
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Tristan Naumann, Asma Ben Abacha, Steven Bethard, Kirk Roberts, Anna Rumshisky
Venue:
ClinicalNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
182–190
Language:
URL:
https://aclanthology.org/2023.clinicalnlp-1.24
DOI:
10.18653/v1/2023.clinicalnlp-1.24
Bibkey:
Cite (ACL):
Giulia Sanguedolce, Patrick A. Naylor, and Fatemeh Geranmayeh. 2023. Uncovering the Potential for a Weakly Supervised End-to-End Model in Recognising Speech from Patient with Post-Stroke Aphasia. In Proceedings of the 5th Clinical Natural Language Processing Workshop, pages 182–190, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Uncovering the Potential for a Weakly Supervised End-to-End Model in Recognising Speech from Patient with Post-Stroke Aphasia (Sanguedolce et al., ClinicalNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.clinicalnlp-1.24.pdf
Video:
 https://aclanthology.org/2023.clinicalnlp-1.24.mp4