Model-agnostic Approaches to Handling Noisy Labels When Training Sound Event Classifiers

TL;DR

This paper evaluates simple, model-agnostic techniques like label smoothing, mixup, and noise-robust loss functions to improve sound event classification accuracy in noisy label scenarios, demonstrating their effectiveness with minimal complexity.

Contribution

It introduces and empirically tests simple, resource-efficient methods for handling noisy labels in sound event classification, filling a gap in existing research.

Findings

Methods improve accuracy by up to 2.5%

Techniques are easy to integrate into existing pipelines

Minimal computational overhead required

Abstract

Label noise is emerging as a pressing issue in sound event classification. This arises as we move towards larger datasets that are difficult to annotate manually, but it is even more severe if datasets are collected automatically from online repositories, where labels are inferred through automated heuristics applied to the audio content or metadata. While learning from noisy labels has been an active area of research in computer vision, it has received little attention in sound event classification. Most recent computer vision approaches against label noise are relatively complex, requiring complex networks or extra data resources. In this work, we evaluate simple and efficient model-agnostic approaches to handling noisy labels when training sound event classifiers, namely label smoothing regularization, mixup and noise-robust loss functions. The main advantage of these methods is that they can be easily incorporated to existing deep learning pipelines without need for network modifications or extra resources. We report results from experiments conducted with the FSDnoisy18k dataset. We show that these simple methods can be effective in mitigating the effect of label noise, providing up to 2.5\% of accuracy boost when incorporated to two different CNNs, while requiring minimal intervention and computational overhead.