Parkinson's disease (PD) and essential tremor (ET) are prevalent movement disorders that mainly affect elderly people, presenting diagnostic challenges due to shared clinical features. While both disorders exhibit distinct speech patterns-hypokinetic dysarthria in PD and hyperkinetic dysarthria in ET-the efficacy of speech assessment for differentiation remains unexplored. Developing technology for automatic discrimination could enable early diagnosis and continuous monitoring. However, the lack of data for investigating speech behavior in these patients has inhibited the development of a framework for diagnostic support. In addition, phonetic variability across languages poses practical challenges in establishing a universal speech assessment system. Therefore, it is necessary to develop models robust to the phonetic variability present in different languages worldwide. We propose a method based on Gaussian mixture models to assess domain adaptation from models trained in German and Spanish to classify PD and ET patients in Czech. We modeled three different speech dimensions: articulation, phonation, and prosody and evaluated the models' performance in both bi-class and tri-class classification scenarios (with the addition of healthy controls). Our results show that a fusion of the three speech dimensions achieved optimal results in binary classification, with accuracies up to 81.4 and 86.2% for monologue and /pa-ta-ka/ tasks, respectively. In tri-class scenarios, incorporating healthy speech signals resulted in accuracies of 63.3 and 71.6% for monologue and /pa-ta-ka/ tasks, respectively. Our findings suggest that automated speech analysis, combined with machine learning is robust, accurate, and can be adapted to different languages to distinguish between PD and ET patients.

• Publication type
• Journal Article MeSH

AIM: To investigate the presence and relationship of temporal speech and gait parameters in patients with postural instability/gait disorder (PIGD) and tremor-dominant (TD) motor subtypes of Parkinson's disease (PD). METHODS: Speech samples and instrumented walkway system assessments were acquired from a total of 60 de-novo PD patients (40 in TD and 20 in PIGD subtype) and 40 matched healthy controls. Objective acoustic vocal assessment of seven distinct speech timing dimensions was related to instrumental gait measures including velocity, cadence, and stride length. RESULTS: Compared to controls, PIGD subtype showed greater consonant timing abnormalities by prolonged voice onset time (VOT) while also shorter stride length during both normal walking and dual task, while decreased velocity and cadence only during dual task. Speaking rate was faster in PIGD than TD subtype. In PIGD subtype, prolonged VOT correlated with slower gait velocity (r = -0.56, p = 0.01) and shorter stride length (r = -0.59, p = 0.008) during normal walking, whereas relationships were also found between decreased cadence in dual task and irregular alternating motion rates (r = -0.48, p = 0.04) and prolonged pauses (r = -0.50, p = 0.03). No correlation between speech and gait was detected in TD subtype. CONCLUSION: Our findings suggest that speech and gait rhythm disorder share similar underlying pathomechanisms specific for PIGD subtype.

• Keywords
• Parkinson's disease, dysarthria, gait, postural instability gait difficulty, speech disorder,
• MeSH
• Gait MeSH
• Walking MeSH
• Humans MeSH
• Gait Disorders, Neurologic * etiology   MeSH
• Parkinson Disease * complications   MeSH
• Postural Balance MeSH
• Speech MeSH
• Tremor MeSH
• Check Tag
• Humans MeSH
• Publication type
• Journal Article MeSH
• Research Support, Non-U.S. Gov't MeSH