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

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 interpretation approach 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 features. We show that the proposed model outperforms a model that learns at a segment level ($p$=0.854, $r$=0.947, $F1$=0.897 compared to $p$=0.732, $r$=0.808, $F1$=0.768). For model interpretation, using one true positive sample, we show which sentences within a given speech are most relevant to depression detection; and which text tokens and Mel-spectrogram regions within these sentences are most relevant to depression detection. These interpretations allow clinicians to verify the validity of predictions made by depression detection tools, promoting their clinical implementations.

This work has been superseded by a later version, submitted as as 'https://arxiv.org/abs/2309.13476', and therefore bears no extra scientific contribution, and should be withdrawn to avoid being cited by the scientific community

Computation and Language (cs.CL); Sound (cs.SD); Audio and Speech Processing (eess.AS)

arXiv:2309.13476 [cs.CL]

(or arXiv:2309.13476v3 [cs.CL] for this version)