Barbera, David S.; Huckvale, Mark; Fleming, Victoria; Upton, Emily; Coley-Fisher, Henry; Doogan, Catherine; Shaw, Ian; Latham, William; Leff, Alexander P. and Crinion, Jenny. 2021. NUVA: A Naming Utterance Verifier for Aphasia Treatment. Computer Speech & Language, 69, 101221. ISSN 0885-2308 [Article]

Preview

Text 1-s2.0-S0885230821000280-main.pdf - Published Version Available under License Creative Commons Attribution. Download (9MB) | Preview

Abstract or Description

Anomia (word-finding difficulties) is the hallmark of aphasia, an acquired language disorder most commonly caused by stroke. Assessment of speech performance using picture naming tasks is a key method for both diagnosis and monitoring of responses to treatment interventions by people with aphasia (PWA). Currently, this assessment is conducted manually by speech and language therapists (SLT). Surprisingly, despite advancements in automatic speech recognition (ASR) and artificial intelligence with technologies like deep learning, research on developing automated systems for this task has been scarce. Here we present NUVA, an utterance verification system incorporating a deep learning element that classifies 'correct' versus' incorrect' naming attempts from aphasic stroke patients. When tested on eight native British-English speaking PWA the system's performance accuracy ranged between 83.6% to 93.6%, with a 10-fold cross-validation mean of 89.5%. This performance was not only significantly better than a baseline created for this study using one of the leading commercially available ASRs (Google speech-to-text service) but also comparable in some instances with two independent SLT ratings for the same dataset.

Item Type:	Article
Identification Number (DOI):	https://doi.org/10.1016/j.csl.2021.101221
Additional Information:	DB and the ASR technical development is funded by a Medical Research Council iCASE PhD studentship, award number 1803748, JC is supported by a Wellcome Trust Senior Research Fellowship in Clinical Science (106161/Z/14/Z), and APL, VF, EU, HCF and CD by an NIHR Research Professorship.
Keywords:	Speech disorders, Word naming, Aphasia, Anomia, Speech recognition, Dynamic Time Warping
Departments, Centres and Research Units:	Computing
Dates:	Date Event 11 March 2021 Accepted 19 March 2021 Published Online September 2021 Published
Item ID:	30401
Date Deposited:	03 Aug 2021 08:15
Last Modified:	03 Aug 2021 15:05
Peer Reviewed:	Yes, this version has been peer-reviewed.
URI:	https://research.gold.ac.uk/id/eprint/30401

View statistics for this item...

Edit Record (login required)