Environment sound classification and recognition method based on D-CNN and KNN technologies

The invention relates to an environmental sound classification and recognition method based on D-CNN and KNN technologies. Compared with the prior art, the method solves the defects that environmental sound classification (ESC) features are difficult to extract, the recognition rate is low and the robustness is poor. The method comprises the following steps: collecting and preprocessing environment sound for training; constructing an environment sound classification and recognition model; training an environment sound classification and recognition model; collecting and preprocessing environment sound to be detected; and obtaining an environment sound classification recognition result. The method not only solves the problem of difficulty in environment sound data feature extraction and improves the accuracy of environment sound recognition, but also enhances the robustness of an environment sound classification recognition algorithm and reaches the practical application level. 本发明涉及一种基于D-CNN和KNN技术的环境声音分类识别方法，