Our study addresses a crucial gap in autism research by delving into linguistic challenges in low-resource languages, often overlooked in prior research primarily focused on English. By investigating unique acoustic and linguistic features in Hindi-speaking CwA, our study aligns with established diagnostic tools and highlights a significant $\boldsymbol{\sim}$9% enhancement in diagnostic accuracy ($\boldsymbol{\sim}$91.3%) for ASD in Hindi-speaking children. Hindi, a non-English language spoken by over 325 million people in India and ranking fifth globally, has been the subject of our pioneering effort, marking the first exploration of ASD speech analysis in this language. This initiative not only represents the first exploration of ASD speech analysis in Hindi but also establishes a precedent for studying linguistic atypicalities in similar resource-constrained languages. The potential impact extends beyond diagnosis, offering promise for enhanced early identification and intervention...

The identification of autism spectrum disorder (ASD) faces challenges due to the lack of reliable biomarkers and the subjectivity in diagnostic procedures, necessitating improved tools for objectivity and efficiency. Being a key characteristic of autism, language impairments are regarded as potential markers for identifying ASD. However, current research predominantly focuses on analyzing language characteristics in English, overlooking linguistic and contextual specificities in other resource-constrained languages. Motivated by these, we developed an artificial intelligence (AI)-based system to detect ASD, utilizing a range of acoustic and linguistic features extracted from dyadic conversations between a child and their communication partner. Validating our model on 76 English-speaking children [35 ASD and 41 typically developing (TD)] and 33 Hindi-speaking children (15 ASD and 18 TD), our extensive analysis of a diverse and comprehensive set of acoustic and linguistic speech attribut...