Synthetic Data Generation Techniques for Developing AI-based Speech Assessments for Parkinson's Disease (A Comparative Study)

TL;DR

This paper investigates how deep learning-generated synthetic speech data can improve AI-based speech assessment systems for early Parkinson's disease detection, addressing data scarcity issues.

Contribution

It provides a comparative analysis of different synthetic data generation techniques and their impact on classifier accuracy for Parkinson's speech assessment.

Findings

Synthetic data improves classifier performance

Deep learning techniques outperform traditional methods

Enhanced data diversity leads to better detection accuracy

Abstract

Changes in speech and language are among the first signs of Parkinson's disease (PD). Thus, clinicians have tried to identify individuals with PD from their voices for years. Doctors can leverage AI-based speech assessments to spot PD thanks to advancements in artificial intelligence (AI). Such AI systems can be developed using machine learning classifiers that have been trained using individuals' voices. Although several studies have shown reasonable results in developing such AI systems, these systems would need more data samples to achieve promising performance. This paper explores using deep learning-based data generation techniques on the accuracy of machine learning classifiers that are the core of such systems.