AudioFuse: Unified Spectral-Temporal Learning via a Hybrid ViT-1D CNN Architecture for Robust Phonocardiogram Classification
Fusing complementary representations provides a strong inductive bias, enabling the creation of efficient, generalizable classifiers without requiring large-scale pre-training.
Md. Saiful Bari Siddiqui, Utsab Saha
· IEEE International Conferenc... · 0 citations