Acoustic characteristics of depression in older adults’ speech: The role of covariates

Carmen Mijnders, Esther Janse, Paul Naarding, Khiet P. Truong

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1 Citation (Scopus)
26 Downloads (Pure)

Abstract

Depression in older adults is often associated with various physical conditions and is hence different from depression at a younger age. Ageing may come with cognitive decline, medication use, and frailty, which are known to be predictors of late-life depression. One common symptom of depression is psychomotor retardation, that may also affect speech production. Most speech studies on depression so far have focused on younger or middle-aged adults. In this study, we used speech data from a large longitudinal Dutch study on late-life depression and its comorbid symptoms to compare speech acoustics in persons with depression (PWD) and controls. We investigated whether groups differed by taking several covariates into account (e.g., frailty, slowness, and medication use). Group differences were found in within-vowel F2 range, speech rate and mean pause duration. These data indicate that speech acoustics can be used to differentiate PWDs and controls, even with low-quality speech data.
Original languageEnglish
Title of host publicationProceedings of INTERSPEECH 2023
EditorsNaomi Harte, Julie Carson-Berndsen, Gareth Jones
Place of PublicationBaixas, France
PublisherInternational Speech Communication Association (ISCA)
Pages4159-4163
DOIs
Publication statusPublished - 2023
Event24th INTERSPEECH 2023 - Dublin, Ireland
Duration: 20 Aug 202324 Aug 2023
Conference number: 24
https://www.interspeech2023.org/

Conference

Conference24th INTERSPEECH 2023
Country/TerritoryIreland
CityDublin
Period20/08/2324/08/23
Internet address

Fingerprint

Dive into the research topics of 'Acoustic characteristics of depression in older adults’ speech: The role of covariates'. Together they form a unique fingerprint.

Cite this