Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification

TL;DR

This paper introduces a novel Patch-Mix Contrastive Learning approach using Audio Spectrogram Transformer for respiratory sound classification, achieving state-of-the-art results by effectively leveraging large-scale pretraining and data augmentation.

Contribution

It proposes a new Patch-Mix augmentation and contrastive learning method that enhances respiratory sound classification performance with limited medical data.

Findings

Achieves 4.08% improvement over previous best on ICBHI dataset

Demonstrates effective transfer from large-scale visual and audio pretraining

Introduces Patch-Mix augmentation for better representation learning

Abstract

Respiratory sound contains crucial information for the early diagnosis of fatal lung diseases. Since the COVID-19 pandemic, there has been a growing interest in contact-free medical care based on electronic stethoscopes. To this end, cutting-edge deep learning models have been developed to diagnose lung diseases; however, it is still challenging due to the scarcity of medical data. In this study, we demonstrate that the pretrained model on large-scale visual and audio datasets can be generalized to the respiratory sound classification task. In addition, we introduce a straightforward Patch-Mix augmentation, which randomly mixes patches between different samples, with Audio Spectrogram Transformer (AST). We further propose a novel and effective Patch-Mix Contrastive Learning to distinguish the mixed representations in the latent space. Our method achieves state-of-the-art performance on the ICBHI dataset, outperforming the prior leading score by an improvement of 4.08%.