Abstract
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%.
| Original language | English |
|---|---|
| Title of host publication | 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024 - Proceedings |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| ISBN (Electronic) | 9798350371499 |
| DOIs | |
| State | Published - 2024 |
| Event | 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024 - Orlando, United States Duration: 15 Jul 2024 → 19 Jul 2024 |
Publication series
| Name | Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS |
|---|---|
| ISSN (Print) | 1557-170X |
Conference
| Conference | 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024 |
|---|---|
| Country/Territory | United States |
| City | Orlando |
| Period | 15/07/24 → 19/07/24 |
UN SDGs
This output contributes to the following UN Sustainable Development Goals (SDGs)
-
SDG 3 Good Health and Well-being
Fingerprint
Dive into the research topics of 'RepAugment: Input-Agnostic Representation-Level Augmentation for Respiratory Sound Classification'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver