Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Learning from Time Series for Health

Predicting Individual Depression Symptoms from Acoustic Features During Speech

Sebastian Rodriguez · Sri Harsha Dumpala · Katerina Dikaios · Sheri Rempel · Rudolf Uher · Sageev Oore


Abstract:

Current automatic depression detection systems provide predictions directly without relying on the individual symptoms/items of depression as denoted in the clinical depression rating scales. In contrast, clinicians assess each item in the depression rating scale in a clinical setting, thus implicitly providing a more detailed rationale for a depression diagnosis. In this work, we make a first step towards using the acoustic features of speech to predict individual items of the depression rating scale before obtaining the final depression prediction. For this, we use convolutional (CNN) and recurrent (long short-term memory (LSTM)) neural networks. We consider different approaches to learning the temporal context of speech. Further, we analyze two variants of voting schemes for individual item prediction and depression detection. We also include an animated visualization that shows an example of item prediction over time as the speech progresses.

Chat is not available.