Research on Audio Recognition Based on the Deep Neural Network in Music Teaching

Table 2

Generalization ability analysis of SPP-YOLO-v4.

Model	Audio file format	Accuracy
		1	2	3	4	Average
YOLO-v4	MPEG	0.931	0.914	0.901	0.933	0.919
	MP3	0.889	0.961	0.894	0.880	0.906
	WMA	0.921	0.910	0.900	0.913	0.911
SPP-YOLO-v4	MPEG	0.951	0.969	0.961	0.959	0.956
	MP3	0.889	0.982	0.911	0.889	0.918
	WMA	0.937	0.989	0.919	0.938	0.945