Cross-linguistic patterns of speech prosodic differences in autism: A machine learning study

Differences in speech prosody are a widely observed feature of Autism Spectrum Disorder (ASD). However, it is unclear how prosodic differences in ASD manifest across different languages that demonstrate cross-linguistic variability in prosody. Using a supervised machine-learning analytic approach, w...

Full description

Saved in:
Bibliographic Details
Published inPloS one Vol. 17; no. 6; p. e0269637
Main Authors Lau, Joseph C. Y., Patel, Shivani, Kang, Xin, Nayar, Kritika, Martin, Gary E., Choy, Jason, Wong, Patrick C. M., Losh, Molly
Format Journal Article
LanguageEnglish
Published United States Public Library of Science 08.06.2022
Public Library of Science (PLoS)
Subjects
Acoustics
Analysis
Auditory stimuli
Autism
Autism Spectrum Disorder - diagnosis
Autistic Disorder
Biology and Life Sciences
Cantonese
Chinese languages
Classification
Computational linguistics
Computer and Information Sciences
Engineering and Technology
English language
Humans
Intonation
Language patterns
Language processing
Languages
Learning algorithms
Linguistics
Machine Learning
Natural language interfaces
Physical Sciences
Prosodic features
Psychological aspects
Rhythm
Rhythms
Social Sciences
Speaking
Speech
Speech Perception
Tonal languages
United States
Online AccessGet full text
ISSN1932-6203
1932-6203
DOI10.1371/journal.pone.0269637

Cover

More Information
Summary:Differences in speech prosody are a widely observed feature of Autism Spectrum Disorder (ASD). However, it is unclear how prosodic differences in ASD manifest across different languages that demonstrate cross-linguistic variability in prosody. Using a supervised machine-learning analytic approach, we examined acoustic features relevant to rhythmic and intonational aspects of prosody derived from narrative samples elicited in English and Cantonese, two typologically and prosodically distinct languages. Our models revealed successful classification of ASD diagnosis using rhythm-relative features within and across both languages. Classification with intonation-relevant features was significant for English but not Cantonese. Results highlight differences in rhythm as a key prosodic feature impacted in ASD, and also demonstrate important variability in other prosodic properties that appear to be modulated by language-specific differences, such as intonation.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
Competing Interests: I also declare that I have read the journal’s policy and the authors of this manuscript have the following competing interests: Patrick C.M. Wong, declares that he is an owner of a startup company supported by a Hong Kong Government technology startup scheme. The research reported here is not associated with the company. This does not alter our adherence to PLOS ONE policies on sharing data and materials. The other authors declare no competing interests exist. All authors have approved the manuscript and have contributed significantly for this research. The minimal dataset and analytic scripts are available from the OSF database (https://osf.io/9ta65/).
ISSN:1932-6203
1932-6203
DOI:10.1371/journal.pone.0269637