Table 1. Description of the experimental set up.

The selected benchmark features correspond to the ones of [29], i.e. 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. These are extracted on the given speech signals $\tilde{s}\left(t\right)$. The configuration employed for the extraction procedure of these features are provided in subsection 7.4. Then, each system model is performed, and the GLRT is applied. Note that, SM1 is considered as benchmark model since it is the proposed reference given standard ASR direclty extract features on the raw data (as done for the bencmark introduced). Further, when it comes to SM2 and SM3, we will consider the first three IMFs or the first three BLIMFs only since they are the ones that detect the great majority of formants required for the classification of Parkinson’s disease. Both the SVM and the GLRT will be done by patient, setting up a text-dependent and a speaker-dependent environment.

Experiment Description
System	Feature	Data	Classifier
				Benchmark	MFCCs, MGDCCs, Jitter,	$\tilde{s}\left(t\right)$	SVM
Shimmer, APQ, PPQ,	$\tilde{s}\left(t\right)$	SVM
RAP, CPP mean, CPP s.d	$\tilde{s}\left(t\right)$	SVM
SM1	GP	$\tilde{s}\left(t\right)$	GLRT
SM2	GP-EMD	γ1(t), γ2(t)γ3(t)	GLRT per IMFs
SM3	GP-EMD	γ1(t)(BL), γ2(t)(BL), γ3(t)(BL)	GLRT per BLIMFs
SM2	EMD-MFCCs	IMF1-MFCCs	SVM per IMFs-MFCCs
		IMF2-MFCCs
		IMF2-MFCCs
SM3	EMD-MFCCs	BLIMF1-MFCCs	SVM per BLIMFs-MFCCs
		BLIMF2-MFCCs
		BLIMF2-MFCCs