Artificial intelligence–based speech assessment in speech disorders: a scoping review

Read full text Summarise with VIRAT
Authors: fang Li
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This project aims to conduct a scoping review on the use of artificial intelligence (AI) in speech assessment for individuals with speech disorders. In recent years, AI-based approaches such as machine learning, deep learning, and automatic speech recognition have been increasingly applied to support speech evaluation. However, existing studies vary widely in terms of methods, populations, and application scenarios, making it difficult to obtain a clear overview of the field. The purpose of this review is to systematically identify and summarize empirical studies that apply AI to speech assessment tasks, including classification, severity rating, and error detection. The review will examine key aspects such as study characteristics, types of speech disorders, speech tasks, AI methods, data sources, and outcome measures. It will also explore how these approaches are used in clinical contexts, such as screening, assessment, and remote monitoring. This review is expected to provide an organized overview of current research, highlight common methodological patterns, and identify existing gaps, particularly in relation to data diversity, model generalizability, and underrepresented populations. The findings may help inform future research and support the development of more practical and clinically relevant AI-based tools for speech assessment.

Fields of Study & Subjects

Voice and Speech Disorders Speech Recognition and Synthesis Language Development and Disorders

Publication details

Publication date
1 January 2026
Language
EN
Document type
Preprint