# Automated speech-based screening of depression using deep convolutional neural networks

arXiv: https://arxiv.org/abs/1912.01115 · HTML: https://mlsanity.com/paper/1912.01115/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Dec 2019.

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

- [The Impact of Speech Anonymization on Pathology and Its Limits](https://mlsanity.com/paper/2404.08064/) (2024)
- [Differential privacy enables fair and accurate AI-based analysis of speech disorders while protecting patient data](https://mlsanity.com/paper/2409.19078/) (2024)
- [Hierarchical Self-Supervised Representation Learning for Depression Detection from Speech](https://mlsanity.com/paper/2510.08593/) (2025)
- [Significance of Speaker Embeddings and Temporal Context for Depression Detection](https://mlsanity.com/paper/2107.13969/) (2021)
- [Medical Speech Symptoms Classification via Disentangled Representation](https://mlsanity.com/paper/2403.05000/) (2024)
- [Perceptual implications of automatic anonymization in pathological speech](https://mlsanity.com/paper/2505.00409/) (2025)
- [DepFlow: Disentangled Speech Generation to Mitigate Semantic Bias in Depression Detection](https://mlsanity.com/paper/2601.00303/) (2026)
- [HiPAD: A Unified Gait, Audio-Visual, and Personality Fusion Network for Depression Detection, with a Hierarchical Personality Ablation and the Calibration Limits of Domain-Adapted LLMs](https://mlsanity.com/paper/2610.14961/) (2026)

## Abstract (arXiv)

Early detection and treatment of depression is essential in promoting remission, preventing relapse, and reducing the emotional burden of the disease. Current diagnoses are primarily subjective, inconsistent across professionals, and expensive for individuals who may be in urgent need of help. This paper proposes a novel approach to automated depression detection in speech using convolutional neural network (CNN) and multipart interactive training. The model was tested using 2568 voice samples obtained from 77 non-depressed and 30 depressed individuals. In experiment conducted, data were applied to residual CNNs in the form of spectrograms, images auto-generated from audio samples. The experimental results obtained using different ResNet architectures gave a promising baseline accuracy reaching 77%.