AudioFuse: Unified Spectral-Temporal Learning via a Hybrid ViT-1D CNN Architecture for Robust Phonocardiogram Classification
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911181800734720 |
|---|---|
| author | Siddiqui, Md. Saiful Bari Saha, Utsab |
| author_facet | Siddiqui, Md. Saiful Bari Saha, Utsab |
| contents | Biomedical audio signals, such as phonocardiograms (PCG), are inherently rhythmic and contain diagnostic information in both their spectral (tonal) and temporal domains. Standard 2D spectrograms provide rich spectral features but compromise the phase information and temporal precision of the 1D waveform. We propose AudioFuse, an architecture that simultaneously learns from both complementary representations to classify PCGs. To mitigate the overfitting risk common in fusion models, we integrate a custom, wide-and-shallow Vision Transformer (ViT) for spectrograms with a shallow 1D CNN for raw waveforms. On the PhysioNet 2016 dataset, AudioFuse achieves a state-of-the-art competitive ROC-AUC of 0.8608 when trained from scratch, outperforming its spectrogram (0.8066) and waveform (0.8223) baselines. Moreover, it demonstrates superior robustness to domain shift on the challenging PASCAL dataset, maintaining an ROC-AUC of 0.7181 while the spectrogram baseline collapses (0.4873). Fusing complementary representations thus provides a strong inductive bias, enabling the creation of efficient, generalizable classifiers without requiring large-scale pre-training. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_23454 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AudioFuse: Unified Spectral-Temporal Learning via a Hybrid ViT-1D CNN Architecture for Robust Phonocardiogram Classification Siddiqui, Md. Saiful Bari Saha, Utsab Audio and Speech Processing Artificial Intelligence Machine Learning Sound Signal Processing Biomedical audio signals, such as phonocardiograms (PCG), are inherently rhythmic and contain diagnostic information in both their spectral (tonal) and temporal domains. Standard 2D spectrograms provide rich spectral features but compromise the phase information and temporal precision of the 1D waveform. We propose AudioFuse, an architecture that simultaneously learns from both complementary representations to classify PCGs. To mitigate the overfitting risk common in fusion models, we integrate a custom, wide-and-shallow Vision Transformer (ViT) for spectrograms with a shallow 1D CNN for raw waveforms. On the PhysioNet 2016 dataset, AudioFuse achieves a state-of-the-art competitive ROC-AUC of 0.8608 when trained from scratch, outperforming its spectrogram (0.8066) and waveform (0.8223) baselines. Moreover, it demonstrates superior robustness to domain shift on the challenging PASCAL dataset, maintaining an ROC-AUC of 0.7181 while the spectrogram baseline collapses (0.4873). Fusing complementary representations thus provides a strong inductive bias, enabling the creation of efficient, generalizable classifiers without requiring large-scale pre-training. |
| title | AudioFuse: Unified Spectral-Temporal Learning via a Hybrid ViT-1D CNN Architecture for Robust Phonocardiogram Classification |
| topic | Audio and Speech Processing Artificial Intelligence Machine Learning Sound Signal Processing |
| url | https://arxiv.org/abs/2509.23454 |