AudioFuse: Unified Spectral-Temporal Learning via a Hybrid ViT-1D CNN Architecture for Robust Phonocardiogram Classification

Md. Saiful Bari Siddiqui, Utsab Saha

Biomedical audio signals, such as phonocardiograms (PCG), are inherently rhythmic and contain diagnostic information in both their spectral (tonal) and temporal domains. Standard 2…