Music Tagging with Classifier Group Chains

2025-01-09

AI Summary

Existing music multi-label classification methods neglect semantic dependencies among labels, resulting in suboptimal annotation accuracy and limited interpretability—particularly hindering music comprehension for non-expert users such as middle-school students. To address this, we propose the Classifier Group Chain (CGC), a novel framework that first partitions labels into semantically coherent groups (e.g., genre, emotion, context) and then constructs an ordered chain across groups to explicitly model inter-group conditional dependencies. We further introduce a mutual information-based strategy for optimal chain ordering and a joint optimization training mechanism. Evaluated on the MTG-Jamendo dataset, CGC achieves significant F1-score improvements over both independent classifiers and standard classifier chains, validating the efficacy of semantic grouping and inter-group dependency modeling. This work is the first to integrate label grouping into the classifier chain paradigm, offering a principled, interpretable, and structurally informed approach to music annotation.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Natural Language Processing: Syntax — Tagging, Chunking & Parsing
• Reasoning under Uncertainty: Graphical Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

We propose music tagging with classifier chains that model the interplay of music tags. Most conventional methods estimate multiple tags independently by treating them as multiple independent binary classification problems. This treatment overlooks the conditional dependencies among music tags, leading to suboptimal tagging performance. Unlike most music taggers, the proposed method sequentially estimates each tag based on the idea of the classifier chains. Beyond the naive classifier chains, the proposed method groups the multiple tags by category, such as genre, and performs chains by unit of groups, which we call extit{classifier group chains}. Our method allows the modeling of the dependence between tag groups. We evaluate the effectiveness of the proposed method for music tagging performance through music tagging experiments using the MTG-Jamendo dataset. Furthermore, we investigate the effective order of chains for music tagging.

Problem

• Music Tagging
• Label Relationship
• Middle School Students

Innovation

• Classifier Chain
• Music Tagging
• Sequential Classifier Application