Hierarchical attention interpretation: an interpretable speech-level transformer for bi-modal depression detection
A bi-modal speech-level transformer is proposed to avoid segment-level labelling and a hierarchical interpretation approach is introduced to provide both speech- level and sentence-level interpretations, based on gradient-weighted attention maps derived from all attention layers to track interactions between input feat...
Qing Deng, S. Luz, Sofia de la Fuente Garcia
· arXiv.org · 1 citation