aiqbench analysis
This paper presents ENACT-Heart, an ensemble model combining Vision Transformers and CNNs to classify heart sounds with high accuracy on the PASCAL dataset. The study demonstrates that late fusion of these architectures yields superior performance metrics compared to individual models, offering a technical advance in audio signal processing via deep learning.
ENACT-Heart -- ENsemble-based Assessment Using CNN and Transformer on Heart Sounds
arXiv:2502.16914v2 Announce Type: replace-cross Abstract: ENACT-Heart is a two-branch ensemble for heart-sound classification. A Vision Transformer (ViT) processes spectrogram images, while a convolutional neural network (CNN) processes visualizations of waveforms and spectral centroids derived from the same recordings. The branch predictions are combined by a weighted average with fixed, input-independent weights. On the PASCAL heart-sound dataset, the ensemble achieved an accuracy of 97.52%, compared with 93.88% for the ViT and 95.45% for the CNN. The ensemble achieved a macro-F1 of 0.94 and recall of 0.74 for extra heart sounds. On this dataset, late fusion improved accuracy and macro-F1 relative to both individual branches.
Abstract:ENACT-Heart is a two-branch ensemble for heart-sound classification. A Vision Transformer (ViT) processes spectrogram images, while a convolutional neural network (CNN) processes visualizations of waveforms and spectral centroids derived from the same recordings. The branch predictions are combined by a weighted average with fixed, input-independent weights. On the PASCAL heart-sound dataset, the ensemble achieved an accuracy of 97.52%, compared with 93.88% for the ViT and 95.45% for the CNN. The ensemble achieved a macro-F1 of 0.94 and recall of 0.74 for extra heart sounds. On this dataset, late fusion improved accuracy and macro-F1 relative to both individual branches.
7 pages. Revised figures and tables, clarified fixed-weight late-fusion terminology, corrected a reference, moderated claims, and reorganized supporting material into appendices. Added an arXiv change log. No new experiments
Sound (cs.SD); Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS)
I.2.6; I.5.4; J.3
arXiv:2502.16914 [cs.SD]
(or arXiv:2502.16914v2 [cs.SD] for this version)
Full text under the publisher's open licence · 148 words