Background & Objective: Hypokinetic arthria mainly associated with Parkinson’s disease. According to Duffy (1995) range of movement, tongue strength, speech rate and voice onset time for stops are reduced. There is an increase in phoneme to phoneme transitions, in syllable and word duration, and in voicing of voiceless stop. Unfortunately patients have physical limitations to reach the clinicians and speech therapists. So the objective of the study was to develop mobile assessment tool to monitor the speech impairments in patients with Parkinson’s disease.

Material And Methods: The data was collected from the study of Goetz et al. (2009), recently summarized in Tsanasetal.(2010a). The data of 120 subjects were collected through the Quantitative Motor Assessment Tool (QMAT) system. Data consisted of both normal and pathological voice. In speech tests, three different types of sentences were spoken by each subject. Each speech test was paired with Unified Parkinson’s Disease Rating Scale (UPDRS) test. 220 twenty audio sample were assessed on the basis of performance of subjects in spoken sentences. The data was used to discriminate healthy and impaired voice in Hypokinetic Dysarthria. For this purpose data is classified in to two classes, Class 0 for healthy voice Class 1 for unhealthy voice. Naïve Bayes classifier (NB) has been used for speech classification. In this proposed system, computerized assessment methods equipped with signal processing and artificial intelligence techniques have been introduced. The sentences used for the measurement of Inter Stress Intervals (ISI) were read by each subject. These sentences were computed for comparisons between normal and impaired voice. The speech features which have been assessed for classification are Energy Entropy, Zero crossing rate (ZCR), Spectral-Centroid, Mean Fundamental-Frequency (Meanf0), Jitter (RAP), Jitter (PPQ), adShimmer (APQ).

Results: For speech test-1 and test-2, 72% and 80% accuracies of classification between healthy and impaired speech samples have been achieved respectively using the NB. For speech test-3, 64% correct classification is achieved using the NB.

Conclusion: The results direct the possibility of speech impairment classification in PD patients based on the clinical rating scale. Future, research will focused on the classification of speech impairment using Unified Parkinson's Disease Rating Scale (UPDRS). This will be helpful for the self-assessment of Patient with Parkinson (PWP) using the mobile device assessment tool.