Voice recognition method and device, electronic equipment and storage medium

The invention discloses a sound recognition method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring first sound data meeting a first requirement; dividing the first sound data into a plurality of identification units; constructing a three-channel picture for feature extraction based on the recognition unit; inputting the three-channel picture into a target neural network to perform feature extraction on the three-channel picture to generate a plurality of feature maps; respectively inputting the feature map into a full connection layer classification network and a comparative learning convolutional network which are connected with the target neural network for processing so as to respectively obtain cross entropy loss data and comparative learning loss data of the feature map; the cross entropy loss data and the comparative learning loss data are fused to generate corresponding loss data, and the loss data are used for training a target neural network;