# Automatic Depression Detection: An Emotional Audio-Textual Corpus and a GRU/BiLSTM-based Model

Source: [Automatic Depression Detection: An Emotional Audio-Textual Corpus and a GRU/BiLSTM-based Model](<https://www.sota2.com/research/paper/68fa5f2e1e209131ce9e814e>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:21.317Z

Authors: Ying Shen, Huiyu Yang, Lin Lin

Published: 2022-02-15T03:29:39.000Z

## Abstract

Depression is a global mental health problem, the worst case of which can lead to suicide. An automatic depression detection system provides great help in facilitating depression self-assessment and improving diagnostic accuracy. In this work, we propose a novel depression detection approach utilizing speech characteristics and linguistic contents from participants' interviews. In addition, we establish an Emotional Audio-Textual Depression Corpus (EATD-Corpus) which contains audios and extracted transcripts of responses from depressed and non-depressed volunteers. To the best of our knowledge, EATD-Corpus is the first and only public depression dataset that contains audio and text data in Chinese. Evaluated on two depression datasets, the proposed method achieves the state-of-the-art performances. The outperforming results demonstrate the effectiveness and generalization ability of the proposed method. The source code and EATD-Corpus are available at https://github.com/speechandlanguageprocessing/ICASSP2022-Depression.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Depression Binary Classification on DepSeverity (test)](<https://www.sota2.com/research/sota/depression-binary-classification-on-depseverity-test.md>): Depression Binary Classification; DepSeverity (test); Accuracy: 84.6.

- [Depression Binary Classification on MMDA (test)](<https://www.sota2.com/research/sota/depression-binary-classification-on-mmda-test.md>): Depression Binary Classification; MMDA (test); Accuracy: 74.5.

- [Depression Recognition on EATD](<https://www.sota2.com/research/sota/depression-recognition-on-eatd.md>): Depression Recognition; EATD; F1 Score: 71.

- [Depression Severity Estimation on MMDA (test)](<https://www.sota2.com/research/sota/depression-severity-estimation-on-mmda-test.md>): Depression Severity Estimation; MMDA (test); Precision (Normal): 38.1.

- [Depression Binary Classification on DR (test)](<https://www.sota2.com/research/sota/depression-binary-classification-on-dr-test.md>): Depression Binary Classification; DR (test); Accuracy: 30.5.

- [Depression Detection on DAIC-WOZ (dev)](<https://www.sota2.com/research/sota/depression-detection-on-daic-woz-dev.md>): Depression Detection; DAIC-WOZ (dev); F1 (avg): 77.34.

- [Depression Severity Estimation on DepSeverity](<https://www.sota2.com/research/sota/depression-severity-estimation-on-depseverity.md>): Depression Severity Estimation; DepSeverity; Precision (Normal): 58.2.

- [Depression Detection on MODMA](<https://www.sota2.com/research/sota/depression-detection-on-modma.md>): Depression Detection; MODMA; F1 Score: 60.4.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2202.08210>)

[PDF](<https://arxiv.org/pdf/2202.08210.pdf>)