Abilities of children with developmental language disorders in perceiving phonological, grammatical, and semantic structures / Georgios P. GEORGIOU in Journal of Autism and Developmental Disorders, 53-11 (November 2023)  

Public ISBD [article]  inJournal of Autism and Developmental Disorders > 53-11 (November 2023) . - p.4483-4487 Titre : Abilities of children with developmental language disorders in perceiving phonological, grammatical, and semantic structures Type de document : texte imprimé Auteurs : Georgios P. GEORGIOU, Auteur ; Elena THEODOROU, Auteur Article en page(s) : p.4483-4487 Langues : Anglais (eng) Index. décimale : PER Périodiques Résumé : This study aims to investigate the perception of phonological, grammatical, and semantic structures by 8 children (age range: 8;2-9;5) with developmental language disorders (DLD). Another 8 age-matched (age range: 8;4-10;0) typically developing (TD) children served as controls. The results demonstrated that children with DLD had lower performance than children with TD in the phonology and grammar tests, corroborating earlier findings, which reported difficulties of children with DLD in discriminating voicing contrasts and perceiving grammatical structures. However, both groups had similar performance in the semantic test. The absence of semantic atypicality can be explained possibly due to the simplicity of the sentences included in the test. The study offers important clinical implications for the identification and treatment of the disorder. En ligne : https://doi.org/10.1007/s10803-022-05548-5 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=512 [article] Abilities of children with developmental language disorders in perceiving phonological, grammatical, and semantic structures [texte imprimé] / Georgios P. GEORGIOU, Auteur ; Elena THEODOROU, Auteur . - p.4483-4487. Langues : Anglais (eng) in Journal of Autism and Developmental Disorders > 53-11 (November 2023) . - p.4483-4487 Index. décimale : PER Périodiques Résumé : This study aims to investigate the perception of phonological, grammatical, and semantic structures by 8 children (age range: 8;2-9;5) with developmental language disorders (DLD). Another 8 age-matched (age range: 8;4-10;0) typically developing (TD) children served as controls. The results demonstrated that children with DLD had lower performance than children with TD in the phonology and grammar tests, corroborating earlier findings, which reported difficulties of children with DLD in discriminating voicing contrasts and perceiving grammatical structures. However, both groups had similar performance in the semantic test. The absence of semantic atypicality can be explained possibly due to the simplicity of the sentences included in the test. The study offers important clinical implications for the identification and treatment of the disorder. En ligne : https://doi.org/10.1007/s10803-022-05548-5 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=512

Correction to: Abilities of Children with Developmental Language Disorders in Perceiving Phonological, Grammatical, and Semantic Structures / Georgios P. GEORGIOU in Journal of Autism and Developmental Disorders, 53-5 (May 2023)  

Public ISBD [article]  inJournal of Autism and Developmental Disorders > 53-5 (May 2023) . - p.2171-2171 Titre : Correction to: Abilities of Children with Developmental Language Disorders in Perceiving Phonological, Grammatical, and Semantic Structures Type de document : texte imprimé Auteurs : Georgios P. GEORGIOU, Auteur ; Elena THEODOROU, Auteur Article en page(s) : p.2171-2171 Langues : Anglais (eng) Index. décimale : PER Périodiques En ligne : https://doi.org/10.1007/s10803-023-05970-3 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=501 [article] Correction to: Abilities of Children with Developmental Language Disorders in Perceiving Phonological, Grammatical, and Semantic Structures [texte imprimé] / Georgios P. GEORGIOU, Auteur ; Elena THEODOROU, Auteur . - p.2171-2171. Langues : Anglais (eng) in Journal of Autism and Developmental Disorders > 53-5 (May 2023) . - p.2171-2171 Index. décimale : PER Périodiques En ligne : https://doi.org/10.1007/s10803-023-05970-3 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=501

Correction to: Identification of Native Vowels in Normal and Whispered Speech by Individuals with Autism Spectrum Disorder / Georgios P. GEORGIOU in Journal of Autism and Developmental Disorders, 53-2 (February 2023)  

Public ISBD [article]  inJournal of Autism and Developmental Disorders > 53-2 (February 2023) . - p.863-863 Titre : Correction to: Identification of Native Vowels in Normal and Whispered Speech by Individuals with Autism Spectrum Disorder Type de document : texte imprimé Auteurs : Georgios P. GEORGIOU, Auteur Article en page(s) : p.863-863 Langues : Anglais (eng) Index. décimale : PER Périodiques Résumé : The corresponding author of this article wants to add his present affiliation and it appears in this erratum. En ligne : https://doi.org/10.1007/s10803-020-04751-6 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=495 [article] Correction to: Identification of Native Vowels in Normal and Whispered Speech by Individuals with Autism Spectrum Disorder [texte imprimé] / Georgios P. GEORGIOU, Auteur . - p.863-863. Langues : Anglais (eng) in Journal of Autism and Developmental Disorders > 53-2 (February 2023) . - p.863-863 Index. décimale : PER Périodiques Résumé : The corresponding author of this article wants to add his present affiliation and it appears in this erratum. En ligne : https://doi.org/10.1007/s10803-020-04751-6 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=495

Identification of Native Vowels in Normal and Whispered Speech by Individuals with Autism Spectrum Disorder / Georgios P. GEORGIOU in Journal of Autism and Developmental Disorders, 53-2 (February 2023)  

Public ISBD [article]  inJournal of Autism and Developmental Disorders > 53-2 (February 2023) . - p.858-862 Titre : Identification of Native Vowels in Normal and Whispered Speech by Individuals with Autism Spectrum Disorder Type de document : texte imprimé Auteurs : Georgios P. GEORGIOU, Auteur Article en page(s) : p.858-862 Langues : Anglais (eng) Index. décimale : PER Périodiques Résumé : The present study aims to investigate the identification of native vowel categories by adult individuals with Autism Spectrum Disorder (ASD) and estimate their reaction times in both normal and whisper registers; their responses were compared with those of typically developing individuals. The results demonstrated that there was no deficit for individuals with ASD in normal speech, but their responses in the whispered speech were impaired. Also, individuals with ASD responded quicker than controls in normal speech but slower in the whispered speech; still, their responses were quicker than the responses of the controls in the whispered mode. The findings can have implications for the understanding of auditory sensitivities and auditory processing time in individuals with ASD as well as for clinical practice. En ligne : https://doi.org/10.1007/s10803-020-04702-1 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=495 [article] Identification of Native Vowels in Normal and Whispered Speech by Individuals with Autism Spectrum Disorder [texte imprimé] / Georgios P. GEORGIOU, Auteur . - p.858-862. Langues : Anglais (eng) in Journal of Autism and Developmental Disorders > 53-2 (February 2023) . - p.858-862 Index. décimale : PER Périodiques Résumé : The present study aims to investigate the identification of native vowel categories by adult individuals with Autism Spectrum Disorder (ASD) and estimate their reaction times in both normal and whisper registers; their responses were compared with those of typically developing individuals. The results demonstrated that there was no deficit for individuals with ASD in normal speech, but their responses in the whispered speech were impaired. Also, individuals with ASD responded quicker than controls in normal speech but slower in the whispered speech; still, their responses were quicker than the responses of the controls in the whispered mode. The findings can have implications for the understanding of auditory sensitivities and auditory processing time in individuals with ASD as well as for clinical practice. En ligne : https://doi.org/10.1007/s10803-020-04702-1 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=495

Machine learning classification of autistic adults using vowel acoustic features / Georgios P. GEORGIOU in Research in Autism, 137 (September 2026)  

Public ISBD [article]  inResearch in Autism > 137 (September 2026) . - 202995 Titre : Machine learning classification of autistic adults using vowel acoustic features Type de document : texte imprimé Auteurs : Georgios P. GEORGIOU, Auteur ; Maria PAPHITI, Auteur Article en page(s) : 202995 Langues : Anglais (eng) Mots-clés : Autism  Machine learning  Speech  Vowels  Explainability Index. décimale : PER Périodiques Résumé : Autism is a neurodevelopmental condition for which timely and accurate identification remains an important clinical priority. Early and reliable identification can facilitate access to assessment, diagnosis, and appropriate support; however, current diagnostic pathways still rely largely on behavioural evaluation and clinical judgement. In this context, machine learning (ML) approaches have attracted growing interest because they can identify subtle and complex patterns in speech data that may not be readily captured through conventional methods. The current study investigated the potential of ML models to distinguish vowel productions from autistic and neurotypical adults based on acoustic speech features. Acoustic measures included fundamental frequency (F0), the first three formants (F1, F2, F3), duration, jitter, shimmer, harmonics-to-noise ratio (HNR), and intensity, elicited through a controlled production task. Four supervised ML models were evaluated: LightGBM, Random Forest, Support Vector Machine, and XGBoost. Under random token-level splitting, all models demonstrated good classification performance, with the best-performing model achieving an area under the curve (AUC) of approximately 0.89. However, performance decreased substantially under speaker-independent cross-validation, with AUCs approximately 0.60 and wider confidence intervals, indicating more limited generalization to vowel productions from unseen speakers. SHAP analyses nevertheless showed a broadly consistent feature-importance pattern across validation schemes, with F0 emerging as the strongest predictor, followed by intensity, while F3 and other acoustic measures made smaller contributions. These findings indicate that vowel acoustics contain information relevant to distinguishing autistic and neurotypical speech within a controlled dataset, while also demonstrating that classification performance is substantially attenuated under speaker-independent validation. The results highlight both the potential of interpretable speech-based ML for investigating acoustic markers of autism and the importance of rigorous speaker-independent evaluation. En ligne : https://doi.org/10.1016/j.reia.2026.202995 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=592 [article] Machine learning classification of autistic adults using vowel acoustic features [texte imprimé] / Georgios P. GEORGIOU, Auteur ; Maria PAPHITI, Auteur . - 202995. Langues : Anglais (eng) in Research in Autism > 137 (September 2026) . - 202995 Mots-clés : Autism  Machine learning  Speech  Vowels  Explainability Index. décimale : PER Périodiques Résumé : Autism is a neurodevelopmental condition for which timely and accurate identification remains an important clinical priority. Early and reliable identification can facilitate access to assessment, diagnosis, and appropriate support; however, current diagnostic pathways still rely largely on behavioural evaluation and clinical judgement. In this context, machine learning (ML) approaches have attracted growing interest because they can identify subtle and complex patterns in speech data that may not be readily captured through conventional methods. The current study investigated the potential of ML models to distinguish vowel productions from autistic and neurotypical adults based on acoustic speech features. Acoustic measures included fundamental frequency (F0), the first three formants (F1, F2, F3), duration, jitter, shimmer, harmonics-to-noise ratio (HNR), and intensity, elicited through a controlled production task. Four supervised ML models were evaluated: LightGBM, Random Forest, Support Vector Machine, and XGBoost. Under random token-level splitting, all models demonstrated good classification performance, with the best-performing model achieving an area under the curve (AUC) of approximately 0.89. However, performance decreased substantially under speaker-independent cross-validation, with AUCs approximately 0.60 and wider confidence intervals, indicating more limited generalization to vowel productions from unseen speakers. SHAP analyses nevertheless showed a broadly consistent feature-importance pattern across validation schemes, with F0 emerging as the strongest predictor, followed by intensity, while F3 and other acoustic measures made smaller contributions. These findings indicate that vowel acoustics contain information relevant to distinguishing autistic and neurotypical speech within a controlled dataset, while also demonstrating that classification performance is substantially attenuated under speaker-independent validation. The results highlight both the potential of interpretable speech-based ML for investigating acoustic markers of autism and the importance of rigorous speaker-independent evaluation. En ligne : https://doi.org/10.1016/j.reia.2026.202995 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=592

---

1 (1 - 5 / 5) Par page : 25 50 100 200