Impact of ASR on Alzheimer’s Disease Detection: All Errors are Equal, but Deletions are More Equal than Others

Aparna Balagopalan, Ksenia Shkaruta, Jekaterina Novikova


Abstract
Automatic Speech Recognition (ASR) is a critical component of any fully-automated speech-based dementia detection model. However, despite years of speech recognition research, little is known about the impact of ASR accuracy on dementia detection. In this paper, we experiment with controlled amounts of artificially generated ASR errors and investigate their influence on dementia detection. We find that deletion errors affect detection performance the most, due to their impact on the features of syntactic complexity and discourse representation in speech. We show the trend to be generalisable across two different datasets for cognitive impairment detection. As a conclusion, we propose optimising the ASR to reflect a higher penalty for deletion errors in order to improve dementia detection performance.
Anthology ID:
2020.wnut-1.21
Volume:
Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020)
Month:
November
Year:
2020
Address:
Online
Venue:
WNUT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
159–164
Language:
URL:
https://aclanthology.org/2020.wnut-1.21
DOI:
10.18653/v1/2020.wnut-1.21
Bibkey:
Cite (ACL):
Aparna Balagopalan, Ksenia Shkaruta, and Jekaterina Novikova. 2020. Impact of ASR on Alzheimer’s Disease Detection: All Errors are Equal, but Deletions are More Equal than Others. In Proceedings of the Sixth Workshop on Noisy User-generated Text (W-NUT 2020), pages 159–164, Online. Association for Computational Linguistics.
Cite (Informal):
Impact of ASR on Alzheimer’s Disease Detection: All Errors are Equal, but Deletions are More Equal than Others (Balagopalan et al., WNUT 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2020.wnut-1.21.pdf
Optional supplementary material:
 2020.wnut-1.21.OptionalSupplementaryMaterial.zip