Table 11.

Results of deep learning classifiers using hybrid features with CTGAN.

MFCC+CTGAN
Model	Class	Precision	Recall	F1 Score	Model	Class	Precision	Recall	F1 Score
LSTM	0	0.00	0.00	0.00	CNN	0	1.00	1.00	1.00
	1	1.00	0.59	0.74		1	1.00	1.00	1.00
	2	0.36	0.01	0.53		2	1.00	1.00	1.00
	Micro avg.	0.45	0.53	0.42		Micro avg.	1.00	1.00	1.00
	Weighted avg.	0.42	0.48	0.39		Weighted avg.	1.00	1.00	1.00
	Accuracy	0.48				Accuracy	1.00
RNN	0	0.71	0.65	0.68	GRU	0	1.00	1.00	1.00
	1	1.00	1.00	1.00		1	1.00	1.00	1.00
	2	0.58	0.64	0.61		2	1.00	1.00	1.00
	Micro avg.	0.76	0.76	0.76		Micro avg.	1.00	1.00	1.00
	Weighted avg.	0.76	0.76	0.76		Weighted avg.	1.00	1.00	1.00
	Accuracy	0.76				Accuracy	1.00

CQT+CTGAN
Model	Class	Precision	Recall	F1 Score	Model	Class	Precision	Recall	F1 Score
LSTM	0	0.40	1.00	0.57	CNN	0	1.00	1.00	1.00
	1	0.00	0.00	0.00		1	1.00	1.00	1.00
	2	0.00	0.00	0.00		2	0.99	0.99	0.99
	Micro avg.	0.13	0.33	0.19		Micro avg.	1.00	1.00	1.00
	Weighted avg.	0.16	0.40	0.22		Weighted avg.	1.00	1.00	1.00
	Accuracy	0.40				Accuracy	1.00
RNN	0	0.58	0.40	0.47	GRU	0	1.00	1.00	1.00
	1	0.53	0.66	0.58		1	1.00	1.00	1.00
	2	0.43	0.50	0.46		2	0.99	1.00	1.00
	Micro avg.	0.51	0.52	0.51		Micro avg.	1.00	1.00	1.00
	Weighted avg.	0.52	0.51	0.50		Weighted avg.	1.00	1.00	1.00
	Accuracy	0.51				Accuracy	1.00