Table 3.

Classification precision (Pre) and negative predictive value (NPV) of several shallow machine learning models (training phase).

Feature/classifier	NB		KNN		LogitReg		RF		SGD		XGB		SVM
	Pre	NPV	Pre	NPV	Pre	NPV	Pre	NPV	Pre	NPV	Pre	NPV	Pre	NPV
Chroma	0.52	0.50	0.53	0.53	0.54	0.54	0.53	0.53	0.55	0.54	0.51	0.51	0.54	0.55
MelSpectrum	0.68	0.55	0.63	0.63	0.64	0.64	0.63	0.61	0.58	0.59	0.61	0.62	0.64	0.63
MFCC	0.55	0.64	0.60	0.62	0.62	0.62	0.63	0.65	0.59	0.59	0.61	0.63	0.68	0.64
PowerSpec	0.54	0.58	0.60	0.60	0.62	0.61	0.66	0.65	0.58	0.57	0.61	0.61	0.63	0.63
RAW	0.59	0.53	0.60	0.59	0.60	0.59	0.58	0.57	0.53	0.52	0.56	0.58	0.61	0.59
Spec	0.56	0.57	0.65	0.66	0.63	0.66	0.68	0.68	0.60	0.62	0.65	0.65	0.73	0.68
Tonal	0.53	0.63	0.53	0.55	0.55	0.55	0.56	0.56	0.51	0.51	0.57	0.53	0.53	0.54