面向鸟鸣声识别任务的深度学习技术

谢卓钒, 李鼎昭, 孙海信, 张安民

Deep learning techniques for bird chirp recognition task

Zhuofan Xie, Dingzhao Li, Haixin Sun, Anmin Zhang

表3 VGG11、ResNet18与DensNet121采用不同特征准确率对比。加粗数值为使用融合特征所得的准确率。

Table 3 Comparison among different feature accuracies of VGG11, ResNet18 and DensNet121. Bold value is the accuracy calculated by the fusion feature.

特征提取方法 Feature extraction method 准确率 Accuracy 总参数量 No. of parameters VGG11 + 原始特征 VGG11 + Original feature 0.906 1.38e8 VGG11 + 对数梅尔谱差分特征 VGG11 + Log-Meier spectral differential characteristics 0.926 1.38e8 VGG11 + 融合特征 VGG11 + Fusion feature 0.935 1.38e8 ResNet18 + 原始特征 ResNet18 + Original feature 0.896 1.11e7 ResNet18 + 对数梅尔谱差分特征 ResNet18 + Log-Meier spectral differential characteristics 0.912 1.11e7 ResNet18 + 融合特征 ResNet18 + Fusion feature 0.933 1.11e7 DensNet121 + 原始特征 DensNet121 + Original feature 0.901 6.94e6 DensNet121 + 对数梅尔谱差分特征 DensNet121 + Log-Meier spectral differential characteristics 0.932 6.96e6 DensNet121 + 融合特征 DensNet121 + Fusion feature 0.939 6.96e6