Open Access
表 2
CNN模型的分类精度 %
| 序号 | 类 | LM | MFCC | GFCC | MGCC |
| 1 | 空调 | 87.4 | 91.7 | 92.7 | 96.7 |
| 2 | 汽车鸣笛 | 75.0 | 62.7 | 82.1 | 86.5 |
| 3 | 儿童玩乐 | 81.5 | 80.8 | 73.0 | 89.9 |
| 4 | 狗叫声 | 60.5 | 78.2 | 68.6 | 80.2 |
| 5 | 钻孔 | 70.8 | 87.7 | 83.2 | 93.0 |
| 6 | 发动机空转 | 91.8 | 93.6 | 93.7 | 94.6 |
| 7 | 枪击 | 28.6 | 72.4 | 52.1 | 57.1 |
| 8 | 凿岩机 | 73.1 | 87.0 | 91.0 | 98.1 |
| 9 | 警笛 | 93.2 | 84.8 | 83.9 | 93.1 |
| 10 | 街头音乐 | 72.5 | 89.9 | 68.7 | 87.4 |
| 平均分类精度 | 73.4 | 82.9 | 78.9 | 87.7 | |
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.