Leveraging Knowledge Bases And Parallel Annotations For Music Genre Translation

TL;DR

This paper introduces a novel approach to predict music genres across different tag systems by combining knowledge-based and statistical translation methods, effectively addressing diversity and subjectivity in genre classification.

Contribution

It proposes a hybrid translation model that unifies diverse genre tag systems using taxonomy mapping and logistic regression, improving genre prediction accuracy.

Findings

Hybrid translation outperforms individual methods in accuracy

Knowledge-based approach effectively maps genre taxonomies

Hybrid model is most effective across different data scenarios

Abstract

Prevalent efforts have been put in automatically inferring genres of musical items. Yet, the propose solutions often rely on simplifications and fail to address the diversity and subjectivity of music genres. Accounting for these has, though, many benefits for aligning knowledge sources, integrating data and enriching musical items with tags. Here, we choose a new angle for the genre study by seeking to predict what would be the genres of musical items in a target tag system, knowing the genres assigned to them within source tag systems. We call this a translation task and identify three cases: 1) no common annotated corpus between source and target tag systems exists, 2) such a large corpus exists, 3) only few common annotations exist. We propose the related solutions: a knowledge-based translation modeled as taxonomy mapping, a statistical translation modeled with maximum likelihood logistic regression; a hybrid translation modeled with maximum a posteriori logistic regression with priors given by the knowledge-based translation. During evaluation, the solutions fit well the identified cases and the hybrid translation is systematically the most effective w.r.t. multilabel classification metrics. This is a first attempt to unify genre tag systems by leveraging both representation and interpretation diversity.