Related Experiment Video
Updated: Jun 24, 2025
08:32
Ultrasound Images of the Tongue: A Tutorial for Assessment and Remediation of Speech Sound Errors
Published on: January 3, 2017
21.8K
Exploring the Role of Machine Learning in Diagnosing and Treating Speech Disorders: A Systematic Literature Review
Zaki Brahmi1, Mohammad Mahyoob2, Mohammed Al-Sarem1
1Department of Computer Science, Taibah University, Madina, Kingdom of Saudi Arabia.
Psychology Research and Behavior Management
|June 5, 2024
Summary
This systematic review analyzes machine learning assistive technologies for speech disorders from 2014-2023. Neural networks and support vector machines are common, with Dysarthria being the most studied condition.
Area of Science:
- Assistive Technology
- Machine Learning
- Speech Pathology
Background:
- Speech disorders significantly impair communication and quality of life.
- A gap exists in systematic reviews of machine learning (ML) assistive technologies for speech disorders.
- This study provides a comprehensive overview of the current landscape.
Purpose of the Study:
- To systematically review ML-based assistive technologies for individuals with speech disorders.
- To offer insights into ML solutions and related research.
- To explore trends in ML techniques, datasets, languages, and feature extraction.
Main Methods:
- A Systematic Literature Review (SLR) methodology was employed.
- The review covered research published between 2014 and 2023.
- Analysis focused on ML techniques, dataset characteristics, languages, and feature extraction.
Main Results:
- 65 papers were analyzed, identifying key trends from 2014-2023.
- Support vector machines (20%) and neural networks (CNN, DNN) (16.92%) were the most used ML techniques.
- Dysarthria was the most studied disorder (54%), with a surge in neural network use post-2018.
Conclusions:
- The study highlights the growing importance of ML in speech disorder assistive technology.
- Neural networks, particularly CNNs and DNNs, show increasing prevalence.
- Further research can leverage these findings to develop more effective assistive solutions.
