Data Augmentation for Instrument Classification Robust to Audio Effects

TL;DR

This paper investigates how data augmentation with audio effects can improve the robustness of automatic instrument classification models used in electronic music production, focusing on classifying processed sounds in audio collections.

Contribution

It evaluates the impact of audio effect-based data augmentation on the robustness of a state-of-the-art instrument classification model.

Findings

Audio effects significantly influence classification accuracy.

Data augmentation improves robustness to processed sounds.

Certain effects reduce model performance more than others.

Abstract

Reusing recorded sounds (sampling) is a key component in Electronic Music Production (EMP), which has been present since its early days and is at the core of genres like hip-hop or jungle. Commercial and non-commercial services allow users to obtain collections of sounds (sample packs) to reuse in their compositions. Automatic classification of one-shot instrumental sounds allows automatically categorising the sounds contained in these collections, allowing easier navigation and better characterisation. Automatic instrument classification has mostly targeted the classification of unprocessed isolated instrumental sounds or detecting predominant instruments in mixed music tracks. For this classification to be useful in audio databases for EMP, it has to be robust to the audio effects applied to unprocessed sounds. In this paper we evaluate how a state of the art model trained with a large dataset of one-shot instrumental sounds performs when classifying instruments processed with audio effects. In order to evaluate the robustness of the model, we use data augmentation with audio effects and evaluate how each effect influences the classification accuracy.