Multiple Musical Instrument Signal Recognition Based on Convolutional Neural Network

Table 7

Comparison between the proposed model and existing methods.

	Piano	Violin	Viola	Guitar	Saxophone	Bassoon tube	Timpani	Xylophone	Bass	Trumpet	Overall accuracy
MA	0.912	0.903	0.849	0.908	0.855	0.859	0.809	0.743	0.762	0.889	0.825
Bipolar classification model	0.913	0.901	0.853	0.907	0.863	0.866	0.822	0.811	0.834	0.880	0.857
Duet	0.827	0.881	—	0.829	—	—	—	—	—	—	0.841
Trio	0.683	0.825	—	0.828	—	—	—	—	—	—	0.778
Quartet	0.573	0.799	—	0.791	—	—	—	—	—	—	0.731