Long short-term memory recurrent neural network based segment features for music genre classification

In the conventional frame feature based music genre classification methods, the audio data is represented by independent frames and the sequential nature of audio is totally ignored. If the sequential knowledge is well modeled and combined, the classification performance can be significantly improved. The long short-term memory(LSTM) recurrent neural network (RNN) which uses a set of special memory cells to model for long-range feature sequence, has been successfully used for many sequence labeling and sequence prediction tasks. In this paper, we propose the LSTM RNN based segment features for music genre classification. The LSTM RNN is used to learn the representation of LSTM frame feature. The segment features are the statistics of frame features in each segment. Furthermore, the LSTM segment feature is combined with the segment representation of initial frame feature to obtain the fusional segment feature. The evaluation on ISMIR database show that the LSTM segment feature performs better than the frame feature. Overall, the fusional segment feature achieves 89.71% classification accuracy, about 4.19% improvement over the baseline model using deep neural network (DNN). This significant improvement show the effectiveness of the proposed segment feature.