Synthetic Data Generation Techniques for Developing AI-based Speech Assessments for Parkinson's Disease (A Comparative Study)
This work addresses the data scarcity issue for developing more effective AI tools to assist clinicians in early detection of Parkinson's disease, but it appears incremental as it builds on existing methods.
The paper tackles the problem of limited data for AI-based speech assessments in Parkinson's disease by exploring deep learning-based synthetic data generation techniques, finding that these methods can improve classifier accuracy, though specific numbers are not provided.
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.