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

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%.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Audio Classification ICBHI Respiratory Sound Database AST (Patch-Mix CL) ICBHI Score 62.37 # 1
Sensitivity 43.07 # 3
Specificity 81.66 # 1
Audio Classification ICBHI Respiratory Sound Database AST (fine-tuning) Sensitivity 41.97 # 6
Specificity 77.14 # 5
Audio Classification ICBHI Respiratory Sound Database AST (fine-tuning) ICBHI Score 59.55 # 5