Transfer Learning of Artist Group Factors to Musical Genre Classification

TL;DR

This paper explores transfer learning techniques that leverage artist group factors to improve music genre classification accuracy, addressing label noise and data availability issues.

Contribution

It introduces a transfer learning framework using artist group factors for genre classification, comparing single-task, multi-task transfer, and multi-task learning approaches.

Findings

Multi-task learning yields the highest validation accuracy.

Artist group factors improve robustness to label noise.

Transfer learning enhances genre classification performance.

Abstract

The automated recognition of music genres from audio information is a challenging problem, as genre labels are subjective and noisy. Artist labels are less subjective and less noisy, while certain artists may relate more strongly to certain genres. At the same time, at prediction time, it is not guaranteed that artist labels are available for a given audio segment. Therefore, in this work, we propose to apply the transfer learning framework, learning artist-related information which will be used at inference time for genre classification. We consider different types of artist-related information, expressed through artist group factors, which will allow for more efficient learning and stronger robustness to potential label noise. Furthermore, we investigate how to achieve the highest validation accuracy on the given FMA dataset, by experimenting with various kinds of transfer methods, including single-task transfer, multi-task transfer and finally multi-task learning.