Multi-modal depression estimation based on sub-attentional fusion

PC Wei, K Peng, A Roitberg, K Yang, J Zhang… - … on Computer Vision, 2022 - Springer
Failure to timely diagnose and effectively treat depression leads to over 280 million people
suffering from this psychological disorder worldwide. The information cues of depression …

Manifestation of depression in speech overlaps with characteristics used to represent and recognize speaker identity

SH Dumpala, K Dikaios, S Rodriguez, R Langley… - Scientific Reports, 2023 - nature.com
The sound of a person's voice is commonly used to identify the speaker. The sound of
speech is also starting to be used to detect medical conditions, such as depression. It is not …

Ensemble learning with speaker embeddings in multiple speech task stimuli for depression detection

Z Liu, H Yu, G Li, Q Chen, Z Ding, L Feng… - Frontiers in …, 2023 - frontiersin.org
Introduction As a biomarker of depression, speech signal has attracted the interest of many
researchers due to its characteristics of easy collection and non-invasive. However, subjects' …

Classifying depression symptom severity: Assessment of speech representations in personalized and generalized machine learning models

EL Campbell, J Dineley, P Conde… - INTERSPEECH …, 2023 - discovery.ucl.ac.uk
There is an urgent need for new methods that improve the management and treatment of
Major Depressive Disorder (MDD). Speech has long been regarded as a promising digital …

Toward corpus size requirements for training and evaluating depression risk models using spoken language

T Rutowski, A Harati, E Shriberg, Y Lu… - arXiv preprint arXiv …, 2024 - arxiv.org
Mental health risk prediction is a growing field in the speech community, but many studies
are based on small corpora. This study illustrates how variations in test and train set sizes …

Mobile Virtual Assistant for Multi-Modal Depression-Level Stratification

EHK Wu, TY Gao, CR Chung, CC Chen… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Depression not only afflicts hundreds of millions of people but also contributes to a global
disability and healthcare burden. The primary method of diagnosing depression relies on …

[PDF][PDF] Detecting depression with a temporal context of speaker embeddings

SH Dumpala, S Rodriguez, S Rempel… - Proc. AAAI …, 2022 - researchgate.net
Depression detection from speech has attracted a lot of attention in recent years. However,
the significance of speakerspecific information in depression detection has not yet been …

Self-supervised embeddings for detecting individual symptoms of depression

SH Dumpala, K Dikaios, A Nunes, F Rudzicz… - arXiv preprint arXiv …, 2024 - arxiv.org
Depression, a prevalent mental health disorder impacting millions globally, demands
reliable assessment systems. Unlike previous studies that focus solely on either detecting …

Deep learning for prominence detection in children's read speech

M Vaidya, K Sabu, P Rao - ICASSP 2022-2022 IEEE …, 2022 - ieeexplore.ieee.org
The detection of perceived prominence in speech has attracted approaches ranging from
the design of knowledge-based linguistic and acoustic features to the automatic feature …

[PDF][PDF] Sine-wave speech and privacy-preserving depression detection

SH Dumpala, R Uher, S Matwin, M Kiefte… - … . SMM21, Workshop on …, 2021 - isca-archive.org
In this work we show that certain characteristics of speech important for depression detection
have future potential to allow privacy preservation. Specifically, we are interested in …