New nonlinear markers and insights into speech signal degradation for effective tracking of Parkinson ’ s disease symptom severity

We have recently shown that speech signal degradation can be used to quantitatively predict average Parkinson‟s disease (PD) symptom severity, which is typically evaluated on the Unified Parkinson‟s Disease Rating Scale (UPDRS). In this study, we demonstrate the potential of wavelets to reveal changes in fundamental frequency variations with PD progression. We develop a set of new measures based on wavelets, energy, and entropy, which form robust indicators of the UPDRS. These results demonstrate that PD leads to dissimilar speech patterns in males and females, tentatively taken to indicate different patho-physiological mechanisms.