Automatic Detection of Apathy using Acoustic Markers extracted from Free Emotional Speech

Abstract : Apathy is a frequent neuropsychiatric syndrome in people with dementia. It leads to diminished motivation for physical, cognitive and emotional activity. Apathy is highly underdiagnosed since its criteria have been only recently established and rely heavily on the subjective evaluation of human observers. In this paper we analyse speech samples from demented people with and without apathy. Speech was provoked by asking patients two emotional questions. Acoustic features were extracted and used in a classification task. The resulting models show performances of AUC = 0:71 and AUC = 0:63. This is a decent first step into the direction of automatic detection of apathy from speech. Usefulness of stimuli to elicit free speech is found to depend on patients gender.
Complete list of metadatas

https://hal.inria.fr/hal-01850436
Contributor : Alexandra König <>
Submitted on : Friday, July 27, 2018 - 12:39:36 PM
Last modification on : Thursday, February 7, 2019 - 5:09:39 PM
Long-term archiving on : Sunday, October 28, 2018 - 1:16:41 PM

File

arial_2018.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01850436, version 1

Collections

Citation

Nicklas Linz, Xenia Klinge, Johannes Tröger, Jan Alexandersson, Radia Zeghari, et al.. Automatic Detection of Apathy using Acoustic Markers extracted from Free Emotional Speech. 2ND WORKSHOP ON AI FOR AGING, REHABILITATION AND INDEPENDENT ASSISTED LIVING (ARIAL) @IJCAI'18, Jul 2018, Stockholm Sweden. ⟨hal-01850436⟩

Share

Metrics

Record views

1028

Files downloads

146