TY - JOUR
T1 - LONGITUDINAL MODELING OF DEPRESSION SHIFTS USING SPEECH AND LANGUAGE
AU - The RADAR-CNS Consortium
AU - Pérez-Toro, Paula Andrea
AU - Dineley, Judith
AU - Kaczkowska, Agnieszka
AU - Conde, Pauline
AU - Zhang, Yuezhou
AU - Matcham, Faith
AU - Siddi, Sara
AU - Haro, Josep Maria
AU - Bruce, Stuart
AU - Wykes, Til
AU - Bailón, Raquel
AU - Vairavan, Srinivasan
AU - Dobson, Richard J.B.
AU - Maier, Andreas
AU - Nöth, Elmar
AU - Orozco-Arroyave, Juan Rafael
AU - Narayan, Vaibhav A.
AU - Hotopf, Matthew
AU - Cummins, Nicholas
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - Speech analysis can provide a potential non-invasive and objective means of assessing and monitoring an individual's mental health. Most studies to date have focused on cross-sectional analysis and have not explored the benefits of speech analysis as a longitudinal monitoring tool that can assist in the management of chronic conditions such as major depressive disorder (MDD). Objectively monitoring for shifts in depression symptom severity levels over time presents a notable challenge, which we address through an automated approach using longitudinal English and Spanish speech samples collected from a clinical population. We employ time-frequency representations and linguistic embeddings to enhance the early recognition of alterations in depression levels in individuals with MDD. We investigate the suitability of using siamese-based training for modeling these changes, intending to enable personalized and adaptive interventions.
AB - Speech analysis can provide a potential non-invasive and objective means of assessing and monitoring an individual's mental health. Most studies to date have focused on cross-sectional analysis and have not explored the benefits of speech analysis as a longitudinal monitoring tool that can assist in the management of chronic conditions such as major depressive disorder (MDD). Objectively monitoring for shifts in depression symptom severity levels over time presents a notable challenge, which we address through an automated approach using longitudinal English and Spanish speech samples collected from a clinical population. We employ time-frequency representations and linguistic embeddings to enhance the early recognition of alterations in depression levels in individuals with MDD. We investigate the suitability of using siamese-based training for modeling these changes, intending to enable personalized and adaptive interventions.
KW - Contrastive Training
KW - Depression
KW - Language Analysis
KW - Longitudinal Assessment
KW - Speech Analysis
UR - http://www.scopus.com/inward/record.url?scp=85195382428&partnerID=8YFLogxK
U2 - 10.1109/ICASSP48485.2024.10447195
DO - 10.1109/ICASSP48485.2024.10447195
M3 - Article
AN - SCOPUS:85195382428
SN - 1520-6149
SP - 12021
EP - 12025
JO - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
JF - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
T2 - 49th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024
Y2 - 14 April 2024 through 19 April 2024
ER -
