Understanding Spoken Language Development of Children with ASD Using Pre-trained Speech Embeddings
This work addresses the need for automated, scalable tools to support early identification and intervention for children with ASD, offering a potential complement to traditional assessment methods.
The paper tackled the problem of assessing spoken language development in children with Autism Spectrum Disorder (ASD) by using pre-trained speech embeddings to classify child vs. adult speech and speech vs. nonverbal vocalization in Natural Language Samples, achieving F1 macro scores of 82.6% and 67.8%.
Speech processing techniques are useful for analyzing speech and language development in children with Autism Spectrum Disorder (ASD), who are often varied and delayed in acquiring these skills. Early identification and intervention are crucial, but traditional assessment methodologies such as caregiver reports are not adequate for the requisite behavioral phenotyping. Natural Language Sample (NLS) analysis has gained attention as a promising complement. Researchers have developed benchmarks for spoken language capabilities in children with ASD, obtainable through the analysis of NLS. This paper proposes applications of speech processing technologies in support of automated assessment of children's spoken language development by classification between child and adult speech and between speech and nonverbal vocalization in NLS, with respective F1 macro scores of 82.6% and 67.8%, underscoring the potential for accurate and scalable tools for ASD research and clinical use.