Lungmix: A Mixup-Based Strategy for Generalization in Respiratory Sound Classification
This work addresses generalization issues in respiratory disease diagnosis for medical applications, representing an incremental improvement in data augmentation methods.
The paper tackles the problem of poor generalization in respiratory sound classification across datasets due to data inconsistencies, introducing Lungmix, a Mixup-based data augmentation technique that improves 4-class classification scores by up to 3.55% and achieves performance comparable to models trained on target datasets.
Respiratory sound classification plays a pivotal role in diagnosing respiratory diseases. While deep learning models have shown success with various respiratory sound datasets, our experiments indicate that models trained on one dataset often fail to generalize effectively to others, mainly due to data collection and annotation \emph{inconsistencies}. To address this limitation, we introduce \emph{Lungmix}, a novel data augmentation technique inspired by Mixup. Lungmix generates augmented data by blending waveforms using loudness and random masks while interpolating labels based on their semantic meaning, helping the model learn more generalized representations. Comprehensive evaluations across three datasets, namely ICBHI, SPR, and HF, demonstrate that Lungmix significantly enhances model generalization to unseen data. In particular, Lungmix boosts the 4-class classification score by up to 3.55\%, achieving performance comparable to models trained directly on the target dataset.