Evaluation of an Automatic Speech Recognition Platform for Dysarthric Speech
Folia Phoniatrica et Logopaedica · 2021 · 73 (5) · 432-441
DOI: 10.1159/000511042 ↗Kurz gefasst
Fachartikel in der Zeitschrift Folia Phoniatrica et Logopaedica, online erschienen am 13.11.2020. Verfasst von Irene Calvo und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurorehabilitation Sciences, Casa Cura Policlinico, Milan, Italy. Hauptthemen laut MEDLINE: Dysarthria, Speech Perception. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 28 Literaturangaben.
Abstract (Originalsprache)
Introduction
The use of commercially available automatic speech recognition (ASR) software is challenged when dysarthria accompanies a physical disability. To overcome this issue, a mobile and personal speech assistant (mPASS) platform was developed, using a speaker-dependent ASR software.
Objective
The aim of this study was to evaluate the performance of the proposed platform and to compare mPASS recognition accuracy to a commercial speaker-independent ASR software. In addition, secondary aims were to investigate the relationship between severity of dysarthria and accuracy and to explore people with dysarthria perceptions on the proposed platform.
Methods
Fifteen individuals with dysarthric speech and 20 individuals with nondysarthric speech recorded 24 words and 5 sentences in a clinical environment. Differences in recognition accuracy between the two systems were evaluated. In addition, mPASS usability was assessed with a technology acceptance model (TAM) questionnaire.
Results
In both groups, mean accuracy rates were significantly higher with mPASS compared to the commercial ASR for words and for sentences. mPASS reached good levels of usefulness and ease of use according to the TAM questionnaire.
Conclusions
Practical applicability of this technology is realistic: the mPASS platform is accurate, and it could be easily used by individuals with dysarthria.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Neurorehabilitation Sciences, Casa Cura Policlinico, Milan, Italy.
- Department of Neurorehabilitation Sciences, Casa Cura Policlinico, Milan, Italy, p.tropea@ccppdezza.it.
- Gido Labs, Poznan, Poland.
Zitieren
APA
Calvo, I., Tropea, P., Viganò, M., Scialla, M., Cavalcante, A. B., Grajzer, M., Gilardone, M., & Corbo, M. (2021). Evaluation of an Automatic Speech Recognition Platform for Dysarthric Speech. Folia Phoniatrica et Logopaedica, 73(5), 432-441. https://doi.org/10.1159/000511042
Vancouver
Calvo I, Tropea P, Viganò M, Scialla M, Cavalcante AB, Grajzer M, et al. Evaluation of an Automatic Speech Recognition Platform for Dysarthric Speech. Folia Phoniatrica et Logopaedica. 2021;73(5):432-441. doi:10.1159/000511042
BibTeX
@article{Calvo2021,
author = {Calvo, Irene and Tropea, Peppino and Viganò, Mauro and Scialla, Maria and Cavalcante, Agnieszka B and Grajzer, Monika and Gilardone, Marco and Corbo, Massimo},
title = {Evaluation of an Automatic Speech Recognition Platform for Dysarthric Speech},
journal = {Folia Phoniatrica et Logopaedica},
year = {2021},
volume = {73},
number = {5},
pages = {432--441},
doi = {10.1159/000511042}
}
EUVIMED