Comparative analysis of GAN-based augmentation pipelines for Parkinson's hypokinetic dysarthria severity detection using deep learning
- 1School of Electronics Engineering, Vellore Institute of Technology , ,
- 2Department of Computer Engineering, VIT Mauritius , ,
Abstract
Class imbalance is a common problem in speech-based severity detection, which can result in biased models and poor recognition of minority severity classes. Generative Adversarial Networks (GANs) have been widely used for data augmentation, but very few studies have comparatively evaluated GAN-based augmentation at different stages of the speech-processing pipeline for assessing Parkinson's hypokinetic dysarthria severity. This paper compares GAN-generated speech (GGS) and GAN-generated image (GGI) augmentation methods for addressing class imbalance in low-frequency cepstrogram-based severity detection using the PC-GITA dataset. GAN-based augmentation was used to generate balanced training datasets using two different augmentation pipelines. The original speech and synthetic speech generated using GGS were converted into low-frequency cepstrogram representations, whereas GGI directly generated low-frequency cepstrogram images. These representations were used as inputs to a CNN trained and evaluated under Speaker-independent (SI) and Speaker-dependent (SD) conditions. In the speaker-independent evaluation, repeated five-fold speaker-stratified cross-validation with five independent random seeds yielded a mean accuracy of 56.47% ± 3.40% for GGS compared to 55.47% ± 3.35% for GGI and 53.13% ± 3.26% for the original-dataset baseline. GGS showed higher mean accuracy, precision, and specificity, whereas GGI showed higher mean recall and F1-score. In the speaker-dependent evaluation, GGI achieved the highest mean accuracy of 76.48% ± 4.09% compared to 73.04% ± 3.63% for GGS and 73.04% ± 3.25% for the original-dataset baseline. However, the speaker-dependent results represent an optimistic upper-bound evaluation because speaker identity was shared between the training and evaluation partitions. In general, the two GAN-based augmentation pipelines showed potential to address class imbalance under the conditions studied, while their relative performance depended on the evaluation protocol and the classification measure.
Related
- Dysarthria and idiopathic Parkinson's disease: a current overview of the relationship between speech impairment and quality of life
- Glenoid inclination in reverse total shoulder arthroplasty with and without baseplate wedge augmentation: a retrospective comparative study
- Comment on Mercurio et al. Outcomes of Acute Achilles Tendon Repair with Platelet-Rich Plasma Augmentation: A Comprehensive Review of Comparative Studies. J. Clin. Med. 2026, 15, 4148.
- Reply to Spiezia et al. Comment on "Mercurio et al. Outcomes of Acute Achilles Tendon Repair with Platelet-Rich Plasma Augmentation: A Comprehensive Review of Comparative Studies. J. Clin. Med. 2026, 15, 4148".
- Arthroscopic Subscapularis Augmentation for the Treatment of Bankart Lesions: A Narrative Review of Indications, Techniques, and Comparative Outcomes
BibTeX
@article{aurobindo2026comparative,
title = {{Comparative analysis of GAN-based augmentation pipelines for Parkinson's hypokinetic dysarthria severity detection using deep learning}},
author = {Aurobindo S and Prakash Ramachandran and Rajesh Kumar M},
journal = {Frontiers in artificial intelligence},
year = {2026},
month = oct,
doi = {10.3389/frai.2026.1951063},
url = {https://europepmc.org/article/PMC/PMC13727737},
note = {CC BY},
}
RIS
TY - JOUR
TI - Comparative analysis of GAN-based augmentation pipelines for Parkinson's hypokinetic dysarthria severity detection using deep learning
AU - Aurobindo S
AU - Prakash Ramachandran
AU - Rajesh Kumar M
PY - 2026
DA - 2026/10/20
JO - Frontiers in artificial intelligence
DO - 10.3389/frai.2026.1951063
UR - https://europepmc.org/article/PMC/PMC13727737
AB - Class imbalance is a common problem in speech-based severity detection, which can result in biased models and poor recognition of minority severity classes. Generative Adversarial Networks (GANs) have been widely used for data augmentation, but very few studies have comparatively evaluated GAN-based augmentation at different stages of the speech-processing pipeline for assessing Parkinson's hypokinetic dysarthria severity. This paper compares GAN-generated speech (GGS) and GAN-generated image (GGI) augmentation methods for addressing class imbalance in low-frequency cepstrogram-based severity detection using the PC-GITA dataset. GAN-based augmentation was used to generate balanced training datasets using two different augmentation pipelines. The original speech and synthetic speech generated using GGS were converted into low-frequency cepstrogram representations, whereas GGI directly generated low-frequency cepstrogram images. These representations were used as inputs to a CNN trained and evaluated under Speaker-independent (SI) and Speaker-dependent (SD) conditions. In the speaker-independent evaluation, repeated five-fold speaker-stratified cross-validation with five independent random seeds yielded a mean accuracy of 56.47% ± 3.40% for GGS compared to 55.47% ± 3.35% for GGI and 53.13% ± 3.26% for the original-dataset baseline. GGS showed higher mean accuracy, precision, and specificity, whereas GGI showed higher mean recall and F1-score. In the speaker-dependent evaluation, GGI achieved the highest mean accuracy of 76.48% ± 4.09% compared to 73.04% ± 3.63% for GGS and 73.04% ± 3.25% for the original-dataset baseline. However, the speaker-dependent results represent an optimistic upper-bound evaluation because speaker identity was shared between the training and evaluation partitions. In general, the two GAN-based augmentation pipelines showed potential to address class imbalance under the conditions studied, while their relative performance depended on the evaluation protocol and the classification measure.
SN - 2624-8212
ER -