# Depression Severity Estimation from Multiple Modalities

arXiv: https://arxiv.org/abs/1711.06095 · HTML: https://mlsanity.com/paper/1711.06095/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Nov 2017.

## Built on by (most cited first, 8 of 8)

- [Multi-modal Depression Estimation based on Sub-attentional Fusion](https://mlsanity.com/paper/2207.06180/) (2022)
- [DepressionEmo: A novel dataset for multilabel classification of depression emotions](https://mlsanity.com/paper/2401.04655/) (2024)
- [Automatic Depression Detection via Learning and Fusing Features from Visual Cues](https://mlsanity.com/paper/2203.00304/) (2022)
- [Leveraging Audio and Text Modalities in Mental Health: A Study of LLMs Performance](https://mlsanity.com/paper/2412.10417/) (2024)
- [Probabilistic Textual Time Series Depression Detection](https://mlsanity.com/paper/2511.04476/) (2025)
- [Let's Give a Voice to Conversational Agents in Virtual Reality](https://mlsanity.com/paper/2308.02665/) (2023)
- [MA-DLE: Speech-based Automatic Depression Level Estimation via Memory Augmentation](https://mlsanity.com/paper/2606.11197/) (2026)
- [Expresso-AI: Explainable Video-Based Deep Learning Models for Depression Diagnosis](https://mlsanity.com/paper/2606.25606/) (2026)

## Abstract (arXiv)

Depression is a major debilitating disorder which can affect people from all ages. With a continuous increase in the number of annual cases of depression, there is a need to develop automatic techniques for the detection of the presence and extent of depression. In this AVEC challenge we explore different modalities (speech, language and visual features extracted from face) to design and develop automatic methods for the detection of depression. In psychology literature, the PHQ-8 questionnaire is well established as a tool for measuring the severity of depression. In this paper we aim to automatically predict the PHQ-8 scores from features extracted from the different modalities. We show that visual features extracted from facial landmarks obtain the best performance in terms of estimating the PHQ-8 results with a mean absolute error (MAE) of 4.66 on the development set. Behavioral characteristics from speech provide an MAE of 4.73. Language features yield a slightly higher MAE of 5.17. When switching to the test set, our Turn Features derived from audio transcriptions achieve the best performance, scoring an MAE of 4.11 (corresponding to an RMSE of 4.94), which makes our system the winner of the AVEC 2017 depression sub-challenge.