Automatic Music Genre Classification using Convolution Neural Network

Music Genre classification is very important in today's world due to rapid growth in music tracks, both online and offline. In order to have better access to these we need to index them accordingly. Automatic music genre classification is important to obtain music from a large collection. Most of the current music genre classification techniques uses machine learning techniques. In this paper, we present a music dataset which includes ten different genres. A Deep Learning approach is used in order to train and classify the system. Here convolution neural network is used for training and classification. Feature Extraction is the most crucial task for audio analysis. Mel Frequency Cepstral Coefficient (MFCC) is used as a feature vector for sound sample. The proposed system classifies music into various genres by extracting the feature vector. Our results show that the accuracy level of our system is around 76% and it will greatly improve and facilitate automatic classification of music genres.