Automatic Assessment of Parkinson’s Disease Using Speech Representations of Phonation and Articulation

Parkinson’s disease (PD) is a progressive neurodegenerative disease that has a high incidence in aging populations. People with PD are likely to suffer from a wide range of motor and non-motor symptoms. Due to the motor disorders, multiple aspects of speech, such as phonation, articulation, and prosody, can be degraded, thereby resulting in poor intelligibility of speech. Motivated to describe articulation deficits comprehensively, we investigated the combination of articulatory and phonation features in PD speech assessment. More specifically, we investigated 1) the universal phonological features that model articulation manner and place, also known as speech attributes, and 2) glottal features capturing phonation characteristics. These were further supplemented by, and compared with, prosodic features using a popular compact feature set (eGeMAPS) and standard Mel-frequency cepstral coefficients. Temporal characteristics of these features were modeled by convolutional neural networks. Besides the features, we were also interested in the speech tasks for collecting data for automatic PD speech assessment. For this, we utilized a recently collected Finnish PD corpus (PDSTU) as well as a Spanish database (PC-GITA). Both speech corpora contain recordings from sustained vowels, text reading, and spontaneous monologue, allowing comparison (and combination) of the tasks in the assessment. The experiments were formulated as regression problems against expert ratings of PD-related symptoms, including ratings of speech intelligibility, voice impairment, overall severity of communication disorder on PDSTU, as well as on the Unified Parkinson’s Disease Rating Scale (UPDRS) on PC-GITA. The experimental results show: 1) the speech attribute features can well indicate the severity of pathologies in parkinsonian speech; 2) combining phonation features with articulatory features improves the PD assessment performance, but requires high-quality recordings to be applicable; 3) read speech leads to more accurate automatic ratings than the use of sustained vowels, but not if the amount of speech is limited to correspond to the sustained vowels in duration; and 4) jointly using data from several speech tasks can further improve the automatic PD assessment performance.Peer reviewe