Hierarchical attention interpretation: an interpretable speech-level transformer for bi-modal depression detection

Excerpt

arXiv:2309.13476v3 Announce Type: replace Abstract: Depression is a common mental disorder. Automatic depression detection tools using speech, enabled by machine learning, help early screening of depression. This paper addresses two limitations that may hinder the clinical implementations of such tools: noise resulting from segment-level labelling and a lack of model interpretability. We propose a bi-modal speech-level transformer to avoid segment-level labelling and introduce a hierarchical int