Research Article
Research on Audio Recognition Based on the Deep Neural Network in Music Teaching
Table 4
Accuracy and detection time of different methods.
| Format | CNN | GMM | R-CNN | SPP-YOLO-v4 | Accuracy | Time (s) | Accuracy | Time (s) | Accuracy | Time (s) | Accuracy | Time (s) |
| CD | 0.960 | 0.459 | 0.987 | 0.448 | 0.973 | 0.456 | 0.994 | 0.454 | WAVE | 0.791 | 0.453 | 0.963 | 0.442 | 0.826 | 0.459 | 0.993 | 0.452 | AIFF | 0.991 | 0.459 | 0.991 | 0.435 | 0.994 | 0.448 | 1.000 | 0.451 | MPEG | 0.970 | 0.473 | 0.990 | 0.448 | 0.994 | 0.457 | 0.997 | 0.443 | MP3 | 0.951 | 0.445 | 0.990 | 0.447 | 0.931 | 0.452 | 0.982 | 0.457 | MPEG-4 | 0.900 | 0.462 | 0.922 | 0.448 | 0.963 | 0.443 | 0.981 | 0.439 | MIDI | 0.907 | 0.460 | 0.870 | 0.449 | 0.901 | 0.451 | 0.982 | 0.448 | WMA | 0.787 | 0.453 | 0.880 | 0.462 | 0.841 | 0.460 | 0.996 | 0.449 | RealAudio | 0.869 | 0.457 | 0.982 | 0.464 | 0.947 | 0.447 | 0.993 | 0.433 | VQF | 0.863 | 0.447 | 0.961 | 0.442 | 0.866 | 0.459 | 0.992 | 0.450 | AMR | 0.957 | 0.453 | 0.960 | 0.443 | 0.990 | 0.459 | 0.991 | 0.451 | AAC | 0.881 | 0.452 | 0.632 | 0.471 | 0.961 | 0.466 | 0.989 | 0.459 | Average | 0.902 | 0.456 | 0.927 | 0.450 | 0.933 | 0.491 | 0.990 | 0.449 |
|
|