An investigation of linguistic stress and articulatory vowel characteristics for automatic depression classification

Brian Stasak, Julien Epps, Roland GOECKE

Research output: Contribution to journalArticle

Abstract

The effects of psychomotor retardation associated with clinical depression are linked to a reduction in variability in acoustic parameters. However, linguistic stress differences between non-depressed and clinically depressed individuals have yet to be investigated. In this paper, by examining vowel articulatory parameters, statistically significant differences in articulatory characteristics are found at a paraphonetic level. For articulatory characteristic features, tongue height and advancement in terms of ‘mid’ and ‘front’ vowel sets show similar depression classification performance trends for both the DAIC-WOZ (English) and AViD (German) databases. Considering linguistic stress feature components, for both databases, depressed speakers exhibit shorter vowel durations and less variance for ‘low’, ‘back’, and ‘rounded’ vowel positions. Results for the DAIC-WOZ and AViD datasets using a small set of linguistic stress based features derived from multiple vowel articulatory parameter sets show absolute, statistically significant, gains of 7% and 20% in two-class depression classification performance over baseline approaches. Linguistic stress feature results indicate that specific vowel set analysis provides better discrimination of clinically depressed and non-depressed speakers. Knowledge gleaned from this research allows the design of more effective automatic depression disorder classification systems.
LanguageEnglish
Pages140-155
Number of pages16
JournalComputer Speech and Language
Volume53
Early online date10 Aug 2018
DOIs
StateE-pub ahead of print - 10 Aug 2018

Fingerprint

Linguistics
Discrimination
Disorder
Baseline
Acoustics

Cite this

@article{9b5d262a780a47c3a8596202f8219db1,
title = "An investigation of linguistic stress and articulatory vowel characteristics for automatic depression classification",
abstract = "The effects of psychomotor retardation associated with clinical depression are linked to a reduction in variability in acoustic parameters. However, linguistic stress differences between non-depressed and clinically depressed individuals have yet to be investigated. In this paper, by examining vowel articulatory parameters, statistically significant differences in articulatory characteristics are found at a paraphonetic level. For articulatory characteristic features, tongue height and advancement in terms of ‘mid’ and ‘front’ vowel sets show similar depression classification performance trends for both the DAIC-WOZ (English) and AViD (German) databases. Considering linguistic stress feature components, for both databases, depressed speakers exhibit shorter vowel durations and less variance for ‘low’, ‘back’, and ‘rounded’ vowel positions. Results for the DAIC-WOZ and AViD datasets using a small set of linguistic stress based features derived from multiple vowel articulatory parameter sets show absolute, statistically significant, gains of 7{\%} and 20{\%} in two-class depression classification performance over baseline approaches. Linguistic stress feature results indicate that specific vowel set analysis provides better discrimination of clinically depressed and non-depressed speakers. Knowledge gleaned from this research allows the design of more effective automatic depression disorder classification systems.",
keywords = "Hypoarticulation, Paralinguistics, Psychomotor retardation, Vowel quadrilateral, Depression",
author = "Brian Stasak and Julien Epps and Roland GOECKE",
year = "2018",
month = "8",
day = "10",
doi = "10.1016/j.csl.2018.08.001",
language = "English",
volume = "53",
pages = "140--155",
journal = "Computer Speech and Language",
issn = "0885-2308",
publisher = "Academic Press Inc.",

}

An investigation of linguistic stress and articulatory vowel characteristics for automatic depression classification. / Stasak, Brian; Epps, Julien; GOECKE, Roland.

In: Computer Speech and Language, Vol. 53, 01.2019, p. 140-155.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An investigation of linguistic stress and articulatory vowel characteristics for automatic depression classification

AU - Stasak,Brian

AU - Epps,Julien

AU - GOECKE,Roland

PY - 2018/8/10

Y1 - 2018/8/10

N2 - The effects of psychomotor retardation associated with clinical depression are linked to a reduction in variability in acoustic parameters. However, linguistic stress differences between non-depressed and clinically depressed individuals have yet to be investigated. In this paper, by examining vowel articulatory parameters, statistically significant differences in articulatory characteristics are found at a paraphonetic level. For articulatory characteristic features, tongue height and advancement in terms of ‘mid’ and ‘front’ vowel sets show similar depression classification performance trends for both the DAIC-WOZ (English) and AViD (German) databases. Considering linguistic stress feature components, for both databases, depressed speakers exhibit shorter vowel durations and less variance for ‘low’, ‘back’, and ‘rounded’ vowel positions. Results for the DAIC-WOZ and AViD datasets using a small set of linguistic stress based features derived from multiple vowel articulatory parameter sets show absolute, statistically significant, gains of 7% and 20% in two-class depression classification performance over baseline approaches. Linguistic stress feature results indicate that specific vowel set analysis provides better discrimination of clinically depressed and non-depressed speakers. Knowledge gleaned from this research allows the design of more effective automatic depression disorder classification systems.

AB - The effects of psychomotor retardation associated with clinical depression are linked to a reduction in variability in acoustic parameters. However, linguistic stress differences between non-depressed and clinically depressed individuals have yet to be investigated. In this paper, by examining vowel articulatory parameters, statistically significant differences in articulatory characteristics are found at a paraphonetic level. For articulatory characteristic features, tongue height and advancement in terms of ‘mid’ and ‘front’ vowel sets show similar depression classification performance trends for both the DAIC-WOZ (English) and AViD (German) databases. Considering linguistic stress feature components, for both databases, depressed speakers exhibit shorter vowel durations and less variance for ‘low’, ‘back’, and ‘rounded’ vowel positions. Results for the DAIC-WOZ and AViD datasets using a small set of linguistic stress based features derived from multiple vowel articulatory parameter sets show absolute, statistically significant, gains of 7% and 20% in two-class depression classification performance over baseline approaches. Linguistic stress feature results indicate that specific vowel set analysis provides better discrimination of clinically depressed and non-depressed speakers. Knowledge gleaned from this research allows the design of more effective automatic depression disorder classification systems.

KW - Hypoarticulation

KW - Paralinguistics

KW - Psychomotor retardation

KW - Vowel quadrilateral

KW - Depression

UR - https://www.sciencedirect.com/science/article/pii/S0885230817303467?via%3Dihub

UR - http://purl.org/au-research/grants/arc/DP130101094

U2 - 10.1016/j.csl.2018.08.001

DO - 10.1016/j.csl.2018.08.001

M3 - Article

VL - 53

SP - 140

EP - 155

JO - Computer Speech and Language

T2 - Computer Speech and Language

JF - Computer Speech and Language

SN - 0885-2308

ER -