In this paper, we propose a new bilinear neural network (BCNN) and apply it to music genre classification. We use Resnet and Densenet which are pre-trained to construct the proposed model . At the end of the two networks, we fuse their output feature and send it to the classifier. Our experiments are carried out on the GTZAN dataset. We extract the mel spectrogram of all the audio in the dataset as the input feature and use the fully connected layer as the classifier to study whether the output

more »

... features of the two classical CNNs are complementary and can achieve better results in this task. Under the same experimental environment and hyperparameters, our proposed BCNN model achieves better classification results than Resnet and Densenet and its classification accuracy is about 81.17%.