Cargando…

Artificial intelligence for the measurement of vocal stereotypy

Both researchers and practitioners often rely on direct observation to measure and monitor behavior. When these behaviors are too complex or numerous to be measured in vivo, relying on direct observation using human observers increases the amount of resources required to conduct research and to moni...

Descripción completa

Detalles Bibliográficos
Autores principales: Dufour, Marie‐Michèle, Lanovaz, Marc J., Cardinal, Patrick
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Wiley Subscription Services, Inc. 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7756764/
https://www.ncbi.nlm.nih.gov/pubmed/33145781
http://dx.doi.org/10.1002/jeab.636
_version_ 1783626612940472320
author Dufour, Marie‐Michèle
Lanovaz, Marc J.
Cardinal, Patrick
author_facet Dufour, Marie‐Michèle
Lanovaz, Marc J.
Cardinal, Patrick
author_sort Dufour, Marie‐Michèle
collection PubMed
description Both researchers and practitioners often rely on direct observation to measure and monitor behavior. When these behaviors are too complex or numerous to be measured in vivo, relying on direct observation using human observers increases the amount of resources required to conduct research and to monitor the effects of interventions in practice. To address this issue, we conducted a proof of concept examining whether artificial intelligence could measure vocal stereotypy in individuals with autism. More specifically, we used an artificial neural network with over 1,500 minutes of audio data from 8 different individuals to train and test models to measure vocal stereotypy. Our results showed that the artificial neural network performed adequately (i.e., session‐by‐session correlation near or above .80 with a human observer) in measuring engagement in vocal stereotypy for 6 of 8 participants. Additional research is needed to further improve the generalizability of the approach.
format Online
Article
Text
id pubmed-7756764
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Wiley Subscription Services, Inc.
record_format MEDLINE/PubMed
spelling pubmed-77567642020-12-28 Artificial intelligence for the measurement of vocal stereotypy Dufour, Marie‐Michèle Lanovaz, Marc J. Cardinal, Patrick J Exp Anal Behav Research Articles Both researchers and practitioners often rely on direct observation to measure and monitor behavior. When these behaviors are too complex or numerous to be measured in vivo, relying on direct observation using human observers increases the amount of resources required to conduct research and to monitor the effects of interventions in practice. To address this issue, we conducted a proof of concept examining whether artificial intelligence could measure vocal stereotypy in individuals with autism. More specifically, we used an artificial neural network with over 1,500 minutes of audio data from 8 different individuals to train and test models to measure vocal stereotypy. Our results showed that the artificial neural network performed adequately (i.e., session‐by‐session correlation near or above .80 with a human observer) in measuring engagement in vocal stereotypy for 6 of 8 participants. Additional research is needed to further improve the generalizability of the approach. Wiley Subscription Services, Inc. 2020-11-03 2020-11 /pmc/articles/PMC7756764/ /pubmed/33145781 http://dx.doi.org/10.1002/jeab.636 Text en © 2020 The Authors. Journal of the Experimental Analysis of Behavior published by Wiley Periodicals LLC on behalf of Society for the Experimental Analysis of Behavior. This is an open access article under the terms of the http://creativecommons.org/licenses/by/4.0/ License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Articles
Dufour, Marie‐Michèle
Lanovaz, Marc J.
Cardinal, Patrick
Artificial intelligence for the measurement of vocal stereotypy
title Artificial intelligence for the measurement of vocal stereotypy
title_full Artificial intelligence for the measurement of vocal stereotypy
title_fullStr Artificial intelligence for the measurement of vocal stereotypy
title_full_unstemmed Artificial intelligence for the measurement of vocal stereotypy
title_short Artificial intelligence for the measurement of vocal stereotypy
title_sort artificial intelligence for the measurement of vocal stereotypy
topic Research Articles
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7756764/
https://www.ncbi.nlm.nih.gov/pubmed/33145781
http://dx.doi.org/10.1002/jeab.636
work_keys_str_mv AT dufourmariemichele artificialintelligenceforthemeasurementofvocalstereotypy
AT lanovazmarcj artificialintelligenceforthemeasurementofvocalstereotypy
AT cardinalpatrick artificialintelligenceforthemeasurementofvocalstereotypy