Prosodic Feature Analysis for Automatic Speech Assessment and Individual Report Generation in People with Down Syndrome

Abstract

Evaluating prosodic quality poses unique challenges due to the intricate nature of prosody, which encompasses multiple form–function profiles. These challenges are more pronounced when analyzing the voices of individuals with Down syndrome (DS) due to increased variability. This paper introduces a procedure for selecting informative prosodic features based on both the disparity between human-rated DS productions and their divergence from the productions of typical users, utilizing a corpus constructed through a video game. Individual reports of five speakers with DS are created by comparing the selected features of each user with recordings of individuals without intellectual disabilities. The acquired features primarily relate to the temporal domain, reducing dependence on pitch detection algorithms, which encounter difficulties when dealing with pathological voices compared to typical ones. These individual reports can be instrumental in identifying specific issues for each speaker, assisting therapists in defining tailored training sessions based on the speaker’s profile.