1D CNN Architectures for Music Genre Classification

This paper proposes a 1D residual convolutional neural network (CNN) architecture for music genre classification and compares it with other recent 1D CNN architectures. The 1D CNNs learn a representation and a discriminant directly from the raw audio signal. Several convolutional layers capture the time-frequency characteristics of the audio signal and learn various filters relevant to the music genre recognition task. The proposed approach splits the audio signal into overlapped segments using a sliding window to comply with the fixed-length input constraint of the 1D CNNs. As a result, music genre classification can be carried out on a single audio segment or on aggregating the predictions on several audio segments, which improves the final accuracy. The performance of the proposed 1D residual CNN is assessed on a public dataset of 1,000 audio clips. The experimental results have shown that it achieves 80.93% of mean accuracy in classifying music genres and outperforms other 1D CNN architectures.

I. Introduction

In the last decade, music has become more and more accessible to everyone across the globe. The exponential growth of musical data has prompted the development of new tools that are more personalized than radio broadcasts, for example. In addition to allowing consumers to listen to their favorite songs, these tools also allow them to discover music from different backgrounds. To such an aim, several approaches to music information retrieval (MIR) have been developed [1]. MIR focuses on researching and developing computational systems to advance the access, organization, and understanding of music information.