Table 3 Performance evaluation of each model based on the dataset in FOA and MIC format
The model name | On FOA format dataset | On MIC format dataset | ||||||
|---|---|---|---|---|---|---|---|---|
DE (\(^\circ\)) | FR (\(\%\)) | ER | F1-score (\(\%\)) | DE (\(^\circ\)) | FR (\(\%\)) | ER | F1-score (\(\%\)) | |
CNN | 19.9 | 81.3 | 0.38 | 75.3 | 19.8 | 75.3 | 0.31 | 81.2 |
CRNN | 21.7 | 63.9 | 0.50 | 63.0 | 21.9 | 63.8 | 0.53 | 62.8 |
Chytas-UTH | 18.6 | 82.4 | 0.29 | 75.6 | 19.8 | 81.2 | 0.31 | 75.3 |
FOA-baseline | 24.6 | 85.4 | 0.28 | 85.7 | 28.5 | 79.9 | 0.34 | 85.4 |
M-CRNN | 27.9 | 86.6 | 0.25 | 85.0 | 30.6 | 85.4 | 0.29 | 83.4 |