arxiv: 1711.11155 · v1 · pith:M7Y3C4CQnew · submitted 2017-11-29 · 💻 cs.CV

Predicting Depression Severity by Multi-Modal Feature Engineering and Fusion

Aven Samareh , Yan Jin , Zhangyang Wang , Xiangyu Chang , Shuai Huang This is my paper

classification 💻 cs.CV

keywords depressionmodeldatafusionpatientproposedseverityacoustic

0 comments p. Extension

Add this Pith Number to your LaTeX paper

\usepackage{pith}
\pithnumber{M7Y3C4CQ}

Prints a linked pith:M7Y3C4CQ badge after your title and writes the identifier into PDF metadata. Compiles on arXiv with no extra files. Learn more

read the original abstract

We present our preliminary work to determine if patient's vocal acoustic, linguistic, and facial patterns could predict clinical ratings of depression severity, namely Patient Health Questionnaire depression scale (PHQ-8). We proposed a multi modal fusion model that combines three different modalities: audio, video , and text features. By training over AVEC 2017 data set, our proposed model outperforms each single modality prediction model, and surpasses the data set baseline with ice margin.

This paper has not been read by Pith yet.

Predicting Depression Severity by Multi-Modal Feature Engineering and Fusion

discussion (0)