RepAugment: Input-Agnostic Representation-Level Augmentation for Respiratory Sound Classification
This work addresses the challenge of improving respiratory sound classification for healthcare applications, but it is incremental as it builds on existing augmentation methods.
The paper tackled the problem of respiratory sound classification by exploring pretrained speech models and addressing the characterization gap between speech and lung sounds with a new augmentation technique. The proposed RepAugment method outperformed SpecAugment, achieving up to a 7.14% improvement in accuracy for minority disease classes.
Recent advancements in AI have democratized its deployment as a healthcare assistant. While pretrained models from large-scale visual and audio datasets have demonstrably generalized to this task, surprisingly, no studies have explored pretrained speech models, which, as human-originated sounds, intuitively would share closer resemblance to lung sounds. This paper explores the efficacy of pretrained speech models for respiratory sound classification. We find that there is a characterization gap between speech and lung sound samples, and to bridge this gap, data augmentation is essential. However, the most widely used augmentation technique for audio and speech, SpecAugment, requires 2-dimensional spectrogram format and cannot be applied to models pretrained on speech waveforms. To address this, we propose RepAugment, an input-agnostic representation-level augmentation technique that outperforms SpecAugment, but is also suitable for respiratory sound classification with waveform pretrained models. Experimental results show that our approach outperforms the SpecAugment, demonstrating a substantial improvement in the accuracy of minority disease classes, reaching up to 7.14%.