Table 7.

Comparison of the proposed combined algorithm CSADT with [53] speech-Sakar dataset with other features except for MFCC and TQWT.

Algorithm	All features except TQWT		All features except MFCC		All features
	Accuracy	F1	Accuracy	F1	Accuracy	F1
NB	0.65	0.67	0.81	0.81	0.83	0.83
LR	0.81	0.79	0.83	0.82	0.85	0.84
KNN	0.82	0.79	0.84	0.82	0.85	0.82
MLP	0.83	0.81	0.81	0.80	0.84	0.83
RF	0.79	0.78	0.83	0.82	0.85	0.84
SVM (linear)	0.81	0.80	0.84	0.83	0.83	0.82
SVM (RBF)	0.83	0.81	0.83	0.81	0.86	0.84
Ensemble	0.81	0.80	0.85	0.84	0.85	0.84
CSADT	0.88	0.85	0.89	0.85	0.93	0.90