# Texture Selection for Automatic Music Genre Classification

## TL;DR

This paper investigates how selecting specific sound textures from music tracks improves automatic genre classification, introducing a novel K-Means based texture selector that enhances performance with fewer textures.

## Contribution

It presents a new texture selection method using K-Means clustering for better genre classification and evaluates its effectiveness across multiple datasets and features.

## Key findings

- Frame selection improves classification accuracy on full-length tracks.
- K-Means texture selector outperforms linear downsampling with fewer textures.
- Texture variety within genres aids model generalization.

## Abstract

Music Genre Classification is the problem of associating genre-related labels to digitized music tracks. It has applications in the organization of commercial and personal music collections. Often, music tracks are described as a set of timbre-inspired sound textures. In shallow-learning systems, the total number of sound textures per track is usually too high, and texture downsampling is necessary to make training tractable. Although previous work has solved this by linear downsampling, no extensive work has been done to evaluate how texture selection benefits genre classification in the context of the bag of frames track descriptions. In this paper, we evaluate the impact of frame selection on automatic music genre classification in a bag of frames scenario. We also present a novel texture selector based on K-Means aimed to identify diverse sound textures within each track. We evaluated texture selection in diverse datasets, four different feature sets, as well as its relationship to a univariate feature selection strategy. The results show that frame selection leads to significant improvement over the single vector baseline on datasets consisting of full-length tracks, regardless of the feature set. Results also indicate that the K-Means texture selector achieves significant improvements over the baseline, using fewer textures per track than the commonly used linear downsampling. The results also suggest that texture selection is complementary to the feature selection strategy evaluated. Our qualitative analysis indicates that texture variety within classes benefits model generalization. Our analysis shows that selecting specific audio excerpts can improve classification performance, and it can be done automatically.