Accuracy performance results of the male patients.

Remark that the accuracy is computed as . The columns show: the UPDRS score (marked as NaN in the case of healthy patients), the benchmark measures performances, corresponding to the MFCCs, MGDCCs, Jitter(%): frequency perturbation, Shimmer (dB): amplitude perturbation, APQ (%): amplitude perturbation quotient, PPQ (%): pitch perturbation quotient, RAP (%): relative average perturbation, CPP mean: mean of cepstral peak prominence corresponding to the mean of voice quality perturbation and CPP s.d.: variation in the cepstral peak prominence corresponding to variation in voice quality perturbation, as given in [29]. Note that the used classifier is the SVM. A cross-validation has been performed for any of the presented results and, therefore, the provided accuracy are the averaged accuracy scores. Configuration for the cross-validation for the benchmark features and the SVM are given in 7.4.