Synthetic Data Augmentation for Medical Audio Classification: A Preliminary Evaluation

TL;DR

This study evaluates the effectiveness of various synthetic data augmentation techniques on respiratory sound classification, finding limited improvements and highlighting the need for task-specific strategies and better evaluation frameworks.

Contribution

It provides a systematic comparison of three generative augmentation methods and their impact on a baseline CNN in medical audio classification, revealing limited benefits.

Findings

Synthetic augmentation did not improve F1-score in most cases.

Ensemble of augmented models achieved a modest performance gain.

Synthetic augmentation may not be universally effective for medical audio tasks.

Abstract

Medical audio classification remains challenging due to low signal-to-noise ratios, subtle discriminative features, and substantial intra-class variability, often compounded by class imbalance and limited training data. Synthetic data augmentation has been proposed as a potential strategy to mitigate these constraints; however, prior studies report inconsistent methodological approaches and mixed empirical results. In this preliminary study, we explore the impact of synthetic augmentation on respiratory sound classification using a baseline deep convolutional neural network trained on a moderately imbalanced dataset (73%:27%). Three generative augmentation strategies (variational autoencoders, generative adversarial networks, and diffusion models) were assessed under controlled experimental conditions. The baseline model without augmentation achieved an F1-score of 0.645. Across individual augmentation strategies, performance gains were not observed, with several configurations demonstrating neutral or degraded classification performance. Only an ensemble of augmented models yielded a modest improvement in F1-score (0.664). These findings suggest that, for medical audio classification, synthetic augmentation may not consistently enhance performance when applied to a standard CNN classifier. Future work should focus on delineating task-specific data characteristics, model-augmentation compatibility, and evaluation frameworks necessary for synthetic augmentation to be effective in medical audio applications.