Neural network-based measure of consonant lenition in Parkinson's Disease

Abstract

This study investigated the effects of Parkinson’s disease (PD) and various linguistic factors on the degree of lenition in Spanish stops. Lenition was estimated from posterior probabilities calculated by recurrent neural networks trained to recognize sonorant and continuant phonological features. Firstly, individuals with PD exhibited a higher degree of lenition in their voiceless stops compared to healthy controls, suggesting that PD significantly impacts the articulatory control of stops, resulting in more pronounced lenition. Secondly, lenition was significantly more advanced for dental stops than bilabial stops, further suggesting that the muscles controlling tongue tip movement are more affected than those involved in lip movement among PD patients. These findings are consistent with previous literature. Importantly, the results highlight the sensitivity of Phonet in quantifying lenition in this group of PD patients.

Publication
Proceedings of Meetings on Acoustics