Identification of cerebellar dysarthria with SISO characterisation

Quantitative identification of dysarthria plays a major role in the classification of its severity. This paper quantitatively analyses several components of cerebellar dysarthria. The methodology described in this study will be extended to other types of dysarthria via systematic analysis. The speech production model is characterized as a second-order single-input and single-output (SISO), linear, time-invariant (LTI) system in our study. A comparative study on the behavior of the damping ratio and resonant frequency for dysarthric and non-dysarthric subjects is presented. The results are further analyzed using the Principal component analysis (PCA) technique to emphasize the variation and uncover strong patterns in the selected features. The effects of some other related factors like decay time and Q-factor are also highlighted.