Speech Corpus for Korean Children with Autism Spectrum Disorder: Towards Automatic Assessment Systems

TL;DR

This paper introduces the first Korean speech corpus for children with Autism Spectrum Disorder (ASD) annotated with social communication severity (SCS) and pronunciation proficiency (PP), addressing the lack of language-specific resources for automatic assessment. Data are collected during standard speech-language evaluations and transcribed with plans to adopt orthographic transcription, enabling both acoustic and linguistic analyses. Initial analyses reveal that MFCCs, CPP, and voice-quality features differentiate ASD subgroups and correlate with SCS and PP, while linguistic features from LFTK show stronger associations with social communication levels. The work demonstrates the potential for automatic SCS and PP assessment and outlines future directions, including fully orthographic analysis and developing predictive models for clinical use.

Abstract

Despite the growing demand for digital therapeutics for children with Autism Spectrum Disorder (ASD), there is currently no speech corpus available for Korean children with ASD. This paper introduces a speech corpus specifically designed for Korean children with ASD, aiming to advance speech technologies such as pronunciation and severity evaluation. Speech recordings from speech and language evaluation sessions were transcribed, and annotated for articulatory and linguistic characteristics. Three speech and language pathologists rated these recordings for social communication severity (SCS) and pronunciation proficiency (PP) using a 3-point Likert scale. The total number of participants will be 300 for children with ASD and 50 for typically developing (TD) children. The paper also analyzes acoustic and linguistic features extracted from speech data collected and completed for annotation from 73 children with ASD and 9 TD children to investigate the characteristics of children with ASD and identify significant features that correlate with the clinical scores. The results reveal some speech and linguistic characteristics in children with ASD that differ from those in TD children or another subgroup of ASD categorized by clinical scores, demonstrating the potential for developing automatic assessment systems for SCS and PP.