Music Genre Classification using Machine Learning Techniques

TL;DR

This paper compares deep learning and traditional machine learning methods for music genre classification, demonstrating that combining spectrogram-based CNNs with handcrafted features improves accuracy on the Audio set dataset.

Contribution

It introduces a hybrid approach that integrates CNN-based deep learning with traditional feature-based classifiers for music genre classification.

Findings

Ensemble classifier achieved an AUC of 0.894.

Hybrid approach outperforms individual models.

Identified key features contributing to classification.

Abstract

Categorizing music files according to their genre is a challenging task in the area of music information retrieval (MIR). In this study, we compare the performance of two classes of models. The first is a deep learning approach wherein a CNN model is trained end-to-end, to predict the genre label of an audio signal, solely using its spectrogram. The second approach utilizes hand-crafted features, both from the time domain and the frequency domain. We train four traditional machine learning classifiers with these features and compare their performance. The features that contribute the most towards this multi-class classification task are identified. The experiments are conducted on the Audio set data set and we report an AUC value of 0.894 for an ensemble classifier which combines the two proposed approaches.