Adversarial Fine-tuning using Generated Respiratory Sound to Address Class Imbalance

TL;DR

This paper introduces a novel adversarial fine-tuning approach using generated respiratory sounds to effectively address class imbalance in respiratory sound classification, outperforming traditional augmentation methods.

Contribution

It proposes a new method combining audio diffusion models and adversarial fine-tuning to improve classification of imbalanced respiratory sound datasets.

Findings

Outperforms baseline by 2.24% on ICBHI Score

Increases minority class accuracy by up to 26.58%

Effective augmentation with adversarial alignment

Abstract

Deep generative models have emerged as a promising approach in the medical image domain to address data scarcity. However, their use for sequential data like respiratory sounds is less explored. In this work, we propose a straightforward approach to augment imbalanced respiratory sound data using an audio diffusion model as a conditional neural vocoder. We also demonstrate a simple yet effective adversarial fine-tuning method to align features between the synthetic and real respiratory sound samples to improve respiratory sound classification performance. Our experimental results on the ICBHI dataset demonstrate that the proposed adversarial fine-tuning is effective, while only using the conventional augmentation method shows performance degradation. Moreover, our method outperforms the baseline by 2.24% on the ICBHI Score and improves the accuracy of the minority classes up to 26.58%. For the supplementary material, we provide the code at https://github.com/kaen2891/adversarial_fine-tuning_using_generated_respiratory_sound.