Research on Musical Sentiment Classification Model Based on Joint Representation Structure
Chunjun Zheng, Ning Jia · Journal of Physics Conference Series · 2019
Abstract In the traditional music emotion classification process, there are problems such as low classification accuracy rate, long period, and difficulty in satisfying the individualized needs of the theme music in people’s lives. Based on this, a neural network model based on joint representation structure is designed. The model uses low-level descriptors and spectrograms to construct a joint representation of the characteristics of the manual and convolutional recurrent neural network, thus realizing the discrimination of music emotion subclasses. At the time of the experiment, the model was designed and the CRNN traditional model was used as the baseline. The experimental results show that this model can improve the classification accuracy of music emotions compared with the traditional single model.