Pronunciation assessment and automated analysis of speech in individuals with Down syndrome: phonetic and fluency dimensions

Abstract

In this study, we analyze the potential use of an annotated corpus to identify various dimensions of speech quality, including phonetics and fluency, in individuals with Down syndrome, enabling the development of automated assessment systems. Two experiments were conducted: for phonetic evaluation, we used the Goodness of Pronunciation (GoP) metric with an automatic segmentation system and correlated results with a speech therapist’s evaluations, showing a positive trend despite not notably high correlation values. For fluency assessment, deep learning models like wav2vec were used to extract audio features, and an SVM classifier trained on a fluency-focused corpus categorized the samples. The outcomes highlight the complexities of evaluating such phenomena, with variability depending on the specific type of disfluency detected.