The Phonetic Footprint of Parkinson's Disease
This work addresses the challenge of analyzing PD speech without requiring pathological training data, which could benefit medical diagnostics and speech analysis tools for patients with neurodegenerative disorders, though it is incremental as it builds on prior research.
The study tackled the problem of analyzing Parkinson's disease (PD) speech by using a phonetic recognizer trained only on healthy speech data, and found that it could rediscover known dysarthric patterns, use neural network activations as disease-related features, and correlate phonetic prediction confidence with expert-rated intelligibility.
As one of the most prevalent neurodegenerative disorders, Parkinson's disease (PD) has a significant impact on the fine motor skills of patients. The complex interplay of different articulators during speech production and realization of required muscle tension become increasingly difficult, thus leading to a dysarthric speech. Characteristic patterns such as vowel instability, slurred pronunciation and slow speech can often be observed in the affected individuals and were analyzed in previous studies to determine the presence and progression of PD. In this work, we used a phonetic recognizer trained exclusively on healthy speech data to investigate how PD affected the phonetic footprint of patients. We rediscovered numerous patterns that had been described in previous contributions although our system had never seen any pathological speech previously. Furthermore, we could show that intermediate activations from the neural network could serve as feature vectors encoding information related to the disease state of individuals. We were also able to directly correlate the expert-rated intelligibility of a speaker with the mean confidence of phonetic predictions. Our results support the assumption that pathological data is not necessarily required to train systems that are capable of analyzing PD speech.