Audio Classification from Time-Frequency Texture

TL;DR

This paper introduces a novel audio classification method that treats spectrograms as texture images, leveraging visual texture classification techniques to effectively identify musical instruments.

Contribution

It presents a simple, texture-based algorithm for audio classification, inspired by visual texture classification, demonstrating strong performance in instrument recognition.

Findings

Effective in musical instrument classification

Treats spectrograms as texture images for classification

Achieves surprisingly good performance

Abstract

Time-frequency representations of audio signals often resemble texture images. This paper derives a simple audio classification algorithm based on treating sound spectrograms as texture images. The algorithm is inspired by an earlier visual classification scheme particularly efficient at classifying textures. While solely based on time-frequency texture features, the algorithm achieves surprisingly good performance in musical instrument classification experiments.