Music Genre Classification Using Independent Recurrent Neural Network

Abstract

Genre is one of the most widely mentioned music labels which have a great influence on accuracy of music recommendation. Machine learning is often used to tackle with genre classification task, but the result of the approach heavily depends on the performance of feature extraction. Deep neural network automatically learns advanced features layer by layer, which makes excellent results in many areas. Music signal is sequential and Recurrent Neural Network (RNN) is widely employed for sequential data. Among variant units of RNN, Independently Recurrent Neural Network (IndRNN) can learn long-term relationship better than popular units such as Long-Short Term Memory (LSTM) and Gated Recurrent Unit (GRU). In addition, IndRNN has better computational efficiency. Consequently, multi-layer IndRNN is used as the main part of our model to classify music genres on the GTZAN dataset. In order to keep the information loss as less as possible, scattering transform is used to preprocess the raw music data. The experimental results show that the model achieves a competitive result in music genre classification task compared with the state-of-the-art models.