A Globally Regularized Joint Neural Architecture for Music Classification

Abstract

Music classification is an essential application of Music Information Retrieval (MIR) in organizing extensive collections of music. The tasks to classify different music with reliable accuracy observed to be challenging. Most of these tasks employ handcrafted feature engineering to build a classifier, yet unable to identify the original characteristics of music. Several combinations of neural networks using convolutional neural networks (CNNs) and recurrent neural networks (RNNs) have been in consideration of many researchers. However, it has been noticed that the joint architecture of CNN and RNN suffers some problems due to batch normalization, which causes low accuracy and more training time. To handle these issues, the Global Layer Regularization (GLR) technique is proposed on the hybrid model of CNN and RNN using Mel-spectrograms for the evaluation of training and accuracy. Our experiments, with few hyper-parameters, improve performance on GTZAN and Free Music Achieve (FMA) datasets by achieving modest accuracy of 87.79% and 68.87% respectively. Empirically, our proposed model takes the advantages of spatiotemporal domain features and the global layer regularization technique to accomplish reliable accuracy as compared to the other state of art works.