Deep Learning for Depression Recognition with Audiovisual Cues: A Review

2021/05/27 by Lang He, Mingyue Niu, He, Lang +21 · 3 citations
Psychology · #Audio and Speech Processing (eess.AS) #Digital Mental Health Interventions #Emotion and Mood Recognition #FOS: Computer and information sciences #FOS: Electrical engineering #Mental Health via Writing #Signal Processing (eess.SP) #Sound (cs.SD) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2106.00610

openalex publication_date 2021/05/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

With the acceleration of the pace of work and life, people have to face more and more pressure, which increases the possibility of suffering from depression. However, many patients may fail to get a timely diagnosis due to the serious imbalance in the doctor-patient ratio in the world. Promisingly, physiological and psychological studies have indicated some differences in speech and facial expression between patients with depression and healthy individuals. Consequently, to improve current medical care, many scholars have used deep learning to extract a representation of depression cues in audio and video for automatic depression detection. To sort out and summarize these works, this review introduces the databases and describes objective markers for automatic depression estimation (ADE). Furthermore, we review the deep learning methods for automatic depression detection to extract the representation of depression from audio and video. Finally, this paper discusses challenges and promising directions related to automatic diagnosing of depression using deep learning technologies.

Citations

• Learning Face Representation from Scratch
• The Inventory of Depressive Symptomatology (IDS): psychometric properties
• A review of depression and suicide risk assessment using speech analysis
• Comparison of Beck Depression Inventories-IA and-II in Psychiatric Outpatients
• Classifying depression patients and normal subjects using machine learning techniques and nonlinear features from EEG signal
• Dynamic Texture Recognition Using Local Binary Patterns with an Application to Facial Expressions
• The Epidemiology of Depression Across Cultures
• A Self-Rating Depression Scale
• Robust Real-Time Face Detection

Cited by

• CLARGA: Multimodal Graph Representation Learning over Arbitrary Sets of Modalities
• Towards Stable Cross-Domain Depression Recognition under Missing Modalities
• MF-GCN: A Multi-Frequency Graph Convolutional Network for Tri-Modal Depression Detection Using Eye-Tracking, Facial, and Acoustic Features

Related

• Automatic Detection of Depression from Stratified Samples of Audio Data
• Exploring Machine Learning and Language Models for Multimodal Depression Detection
• Reading Between the Frames: Multi-Modal Depression Detection in Videos from Non-Verbal Cues
• The Verbal and Non Verbal Signals of Depression -- Combining Acoustics, Text and Visuals for Estimating Depression Level
• Depression Scale Recognition from Audio, Visual and Text Analysis