Toggle Main Menu Toggle Search

Open Access padlockePrints

Deep learning-based automated speech detection as a marker of social functioning in late-life depression

Lookup NU author(s): Dr Beth LittleORCiD, Ossama Alshabrawy, Dr Daniel StowORCiD, Emeritus Professor Nicol Ferrier, Dr Rosin McNaney, Dan Jackson, Dr Thomas Ploetz, Professor Jaume Bacardit, Professor Patrick OlivierORCiD, Dr Peter GallagherORCiD, Professor John O'Brien



This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).


Background: Late-life depression (LLD) is associated with poor social functioning. However, previous research uses bias-prone self-report scales to measure social functioning and a more objective measure is lacking. We tested a novel wearable device to measure speech that participants encounter as an indicator of social interaction. Methods: 29 participants with LLD and 29 age-matched controls wore a wrist-worn device continuously for seven days, which recorded their acoustic environment. Acoustic data were automatically analysed using deep learning models that had been developed and validated on an independent speech dataset. Total speech activity and the proportion of speech produced by the device wearer were both detected whilst maintaining participants’ privacy. Participants underwent a neuropsychological test battery and clinical and self-report scales to measure severity of depression, general and social functioning. Results: Compared to controls, participants with LLD showed poorer self-reported social and general functioning. Total speech activity was much lower for participants with LLD than controls, with no overlap between groups. The proportion of speech produced by the participants was smaller for LLD than controls. In LLD, both speech measures correlated with attention and psychomotor speed performance but not with depression severity or self-reported social functioning. Conclusions: Using this device, LLD was associated with lower levels of speech than controls and speech activity was related to psychomotor retardation. We have demonstrated that speech activity measured by wearable technology differentiated LLD from controls with high precision and, in this study, provided an objective measure of an aspect of real-world social functioning in LLD.

Publication metadata

Author(s): Little B, Alshabrawy O, Stow D, Ferrier IN, McNaney R, Jackson DG, Ladha K, Ladha C, Ploetz T, Bacardit J, Olivier P, Gallagher P, OBrien JT

Publication type: Article

Publication status: Published

Journal: Psychological Medicine

Year: 2021

Volume: 51

Issue: 9

Pages: 1441-1450

Print publication date: 01/07/2021

Online publication date: 16/01/2020

Acceptance date: 13/12/2019

Date deposited: 16/12/2019

ISSN (print): 0033-2917

ISSN (electronic): 1469-8978

Publisher: Cambridge University Press


DOI: 10.1017/S0033291719003994


Altmetrics provided by Altmetric


Funder referenceFunder name