Robustness of musical features on deep learning models for music genre classification

Abstract

Music information retrieval (MIR) has witnessed rapid advances in various tasks like musical similarity, music genre classification (MGC), etc. MGC and audio tagging are approached using various features through traditional machine learning and deep learning (DL) based techniques by many researchers. DL-based models require a large amount of data to generalize well on new data samples. Unfortunately, the lack of sizeable open music datasets makes the analyses of the robustness of musical features on DL models even more necessary. So, this paper assesses and compares the robustness of some commonly used musical and non-musical features on DL models for the MGC task by evaluating the performance of selected models on multiple employed features extracted from various datasets accounting for billions of segmented data samples. In our evaluation, Mel-Scale based features and Swaragram showed high robustness across the datasets over various DL models for the MGC task.