# MFCC-based Recurrent Neural Network for Automatic Clinical Depression Recognition and Assessment from Speech

arXiv: https://arxiv.org/abs/1909.07208 · HTML: https://mlsanity.com/paper/1909.07208/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2019.

## Built on by (most cited first, 18 of 18)

- [Leveraging Recent Advances in Deep Learning for Audio-Visual Emotion Recognition](https://mlsanity.com/paper/2103.09154/) (2021)
- [Deep Transfer Learning for Automatic Speech Recognition: Towards Better Generalization](https://mlsanity.com/paper/2304.14535/) (2023)
- [DEPAC: a Corpus for Depression and Anxiety Detection from Speech](https://mlsanity.com/paper/2306.12443/) (2023)
- [PTSD in the Wild: A Video Database for Studying Post-Traumatic Stress Disorder Recognition in Unconstrained Environments](https://mlsanity.com/paper/2209.14085/) (2022)
- [Explainable Depression Detection via Head Motion Patterns](https://mlsanity.com/paper/2307.12241/) (2023)
- [Computational Analysis of Stress, Depression and Engagement in Mental Health: A Survey](https://mlsanity.com/paper/2403.08824/) (2024)
- [Automatic Depression Assessment using Machine Learning: A Comprehensive Survey](https://mlsanity.com/paper/2506.18915/) (2025)
- [Hierarchical Self-Supervised Representation Learning for Depression Detection from Speech](https://mlsanity.com/paper/2510.08593/) (2025)
- [The Relationship Between Speech Features Changes When You Get Depressed: Feature Correlations for Improving Speed and Performance of Depression Detection](https://mlsanity.com/paper/2307.02892/) (2023)
- [Deep Insights into Cognitive Decline: A Survey of Leveraging Non-Intrusive Modalities with Deep Learning Techniques](https://mlsanity.com/paper/2410.18972/) (2024)
- [Clinically Inspired Symptom-Guided Depression Detection from Emotion-Aware Speech Representations](https://mlsanity.com/paper/2602.15578/) (2026)
- [Detecting the Severity of Major Depressive Disorder from Speech: A Novel HARD-Training Methodology](https://mlsanity.com/paper/2206.01542/) (2022)
- [Optimising MFCC parameters for the automatic detection of respiratory diseases](https://mlsanity.com/paper/2408.07522/) (2024)
- [Unified Pathological Speech Analysis with Prompt Tuning](https://mlsanity.com/paper/2411.04142/) (2024)
- [Audio Frequency-Time Dual Domain Evaluation on Depression Diagnosis](https://mlsanity.com/paper/2510.22225/) (2025)
- [MF-GCN: A Multi-Frequency Graph Convolutional Network for Tri-Modal Depression Detection Using Eye-Tracking, Facial, and Acoustic Features](https://mlsanity.com/paper/2511.15675/) (2025)
- [Foundation Model-based Evaluation of Neuropsychiatric Disorders: A Lifespan-Inclusive, Multi-Modal, and Multi-Lingual Study](https://mlsanity.com/paper/2512.20948/) (2025)
- [TAAC: A gate into Trustable Audio Affective Computing](https://mlsanity.com/paper/2603.25570/) (2026)

## Abstract (arXiv)

Clinical depression or Major Depressive Disorder (MDD) is a common and serious medical illness. In this paper, a deep recurrent neural network-based framework is presented to detect depression and to predict its severity level from speech. Low-level and high-level audio features are extracted from audio recordings to predict the 24 scores of the Patient Health Questionnaire and the binary class of depression diagnosis. To overcome the problem of the small size of Speech Depression Recognition (SDR) datasets, expanding training labels and transferred features are considered. The proposed approach outperforms the state-of-art approaches on the DAIC-WOZ database with an overall accuracy of 76.27% and a root mean square error of 0.4 in assessing depression, while a root mean square error of 0.168 is achieved in predicting the depression severity levels. The proposed framework has several advantages (fastness, non-invasiveness, and non-intrusion), which makes it convenient for real-time applications. The performances of the proposed approach are evaluated under a multi-modal and a multi-features experiments. MFCC based high-level features hold relevant information related to depression. Yet, adding visual action units and different other acoustic features further boosts the classification results by 20% and 10% to reach an accuracy of 95.6% and 86%, respectively. Considering visual-facial modality needs to be carefully studied as it sparks patient privacy concerns while adding more acoustic features increases the computation time.