Multidimensional Acoustic–Prosodic Quantification Framework Using Unscripted Speech for Autism Spectrum Disorder Identification / Minghao DU in Autism Research, 19-4 (April 2026)  

Public ISBD [article]  inAutism Research > 19-4 (April 2026) . - e70206 Titre : Multidimensional Acoustic–Prosodic Quantification Framework Using Unscripted Speech for Autism Spectrum Disorder Identification Type de document : texte imprimé Auteurs : Minghao DU, Auteur ; Ping SHI, Auteur ; Zehao LIU, Auteur ; Xiaoyao LU, Auteur ; Luling CAO, Auteur ; Beibei LIU, Auteur ; Xiaoya LIU, Auteur ; Wei LIU, Auteur ; Shuang LIU, Auteur ; Dong MING, Auteur Article en page(s) : e70206 Langues : Anglais (eng) Mots-clés : acoustic analysis  autism spectrum disorder  classification  speech Index. décimale : PER Périodiques Résumé : ABSTRACT Although clinical observations have noted early speech abnormalities in children with autism spectrum disorder (ASD), automatic speech-based detection remains challenging. This is primarily due to the reliance on scripted tasks, which younger children often struggle to complete and which are not generalizable to large-scale, non-clinical screening. To address this, we developed an unscripted speech-based framework to quantify atypical acoustic?prosodic patterns for automatic ASD identification in naturalistic interactions. It processes free-flowing conversations, extracts multidimensional acoustic features from the time and frequency domains, and models ASD-related prosodic patterns for classification. For evaluation, we collected spontaneous speech from 88 children with ASD (3?10?years) and 82 typically developing (TD) children (3?9?years) during naturalistic interactions on daily topics (e.g., toys, animated movies, storybook reading). Group comparisons revealed atypical prosodic patterns in ASD, including reduced speech continuity, speech rate, and Formant 3, alongside increased zero-crossing rate, pitch, pitch variability, and Formant 1 (all p??0.05), but a pronounced effect of speech context (p? En ligne : https://doi.org/10.1002/aur.70206 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=585 [article] Multidimensional Acoustic–Prosodic Quantification Framework Using Unscripted Speech for Autism Spectrum Disorder Identification [texte imprimé] / Minghao DU, Auteur ; Ping SHI, Auteur ; Zehao LIU, Auteur ; Xiaoyao LU, Auteur ; Luling CAO, Auteur ; Beibei LIU, Auteur ; Xiaoya LIU, Auteur ; Wei LIU, Auteur ; Shuang LIU, Auteur ; Dong MING, Auteur . - e70206. Langues : Anglais (eng) in Autism Research > 19-4 (April 2026) . - e70206 Mots-clés : acoustic analysis  autism spectrum disorder  classification  speech Index. décimale : PER Périodiques Résumé : ABSTRACT Although clinical observations have noted early speech abnormalities in children with autism spectrum disorder (ASD), automatic speech-based detection remains challenging. This is primarily due to the reliance on scripted tasks, which younger children often struggle to complete and which are not generalizable to large-scale, non-clinical screening. To address this, we developed an unscripted speech-based framework to quantify atypical acoustic?prosodic patterns for automatic ASD identification in naturalistic interactions. It processes free-flowing conversations, extracts multidimensional acoustic features from the time and frequency domains, and models ASD-related prosodic patterns for classification. For evaluation, we collected spontaneous speech from 88 children with ASD (3?10?years) and 82 typically developing (TD) children (3?9?years) during naturalistic interactions on daily topics (e.g., toys, animated movies, storybook reading). Group comparisons revealed atypical prosodic patterns in ASD, including reduced speech continuity, speech rate, and Formant 3, alongside increased zero-crossing rate, pitch, pitch variability, and Formant 1 (all p??0.05), but a pronounced effect of speech context (p? En ligne : https://doi.org/10.1002/aur.70206 Permalink : https://www.cra-rhone-alpes.org/cid/opac_css/index.php?lvl=notice_display&id=585

---

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