Elicitation design for acoustic depression classification: An investigation of articulation effort, linguistic complexity, and word affect

Brian Stasak, Julien Epps, Roland Goecke

Research output: A Conference proceeding or a Chapter in BookConference contribution

8 Citations (Scopus)

Abstract

Assessment of neurological and psychiatric disorders like depression are unusual from a speech processing perspective, in that speakers can be prompted or instructed in what they should say (e.g. as part of a clinical assessment). Despite prior speech-based depression studies that have used a variety of speech elicitation methods, there has been little evaluation of the best elicitation mode. One approach to understand this better is to analyze an existing database from the perspective of articulation effort, word affect, and linguistic complexity measures as proxies for depression sub-symptoms (e.g. psychomotor retardation, negative stimulus suppression, cognitive impairment). Here a novel measure for quantifying articulation effort is introduced, and when applied experimentally to the DAIC corpus shows promise for identifying speech data that are more discriminative of depression. Interestingly, experiment results demonstrate that by selecting speech with higher articulation effort, linguistic complexity, or word-based arousal/valence, improvements in acoustic speech-based feature depression classification performance can be achieved, serving as a guide for future elicitation design.

Original languageEnglish
Title of host publicationProceedings of Interspeech 2017
Place of PublicationStockholm, Sweden
PublisherInternational Speech Communication Association (ISCA)
Pages834-838
Number of pages5
DOIs
Publication statusPublished - 20 Aug 2017
Event18th Annual Conference of the International Speech Communication Association, INTERSPEECH 2017 - Stockholm, Sweden
Duration: 20 Aug 201724 Aug 2017

Publication series

NameProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
ISSN (Print)2308-457X

Conference

Conference18th Annual Conference of the International Speech Communication Association, INTERSPEECH 2017
CountrySweden
CityStockholm
Period20/08/1724/08/17

Fingerprint

Elicitation
Linguistics
Acoustics
Speech Processing
Complexity Measure
Speech processing
Disorder
Speech
Design
Articulation
Linguistic Complexity
Evaluation
Demonstrate
Experiment

Cite this

Stasak, B., Epps, J., & Goecke, R. (2017). Elicitation design for acoustic depression classification: An investigation of articulation effort, linguistic complexity, and word affect. In Proceedings of Interspeech 2017 (pp. 834-838). (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH). Stockholm, Sweden: International Speech Communication Association (ISCA). https://doi.org/10.21437/Interspeech.2017-1223
Stasak, Brian ; Epps, Julien ; Goecke, Roland. / Elicitation design for acoustic depression classification: An investigation of articulation effort, linguistic complexity, and word affect. Proceedings of Interspeech 2017. Stockholm, Sweden : International Speech Communication Association (ISCA), 2017. pp. 834-838 (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH).
@inproceedings{5cbbe4eaf9a349f3a8f9f5d570d6f11f,
title = "Elicitation design for acoustic depression classification: An investigation of articulation effort, linguistic complexity, and word affect",
abstract = "Assessment of neurological and psychiatric disorders like depression are unusual from a speech processing perspective, in that speakers can be prompted or instructed in what they should say (e.g. as part of a clinical assessment). Despite prior speech-based depression studies that have used a variety of speech elicitation methods, there has been little evaluation of the best elicitation mode. One approach to understand this better is to analyze an existing database from the perspective of articulation effort, word affect, and linguistic complexity measures as proxies for depression sub-symptoms (e.g. psychomotor retardation, negative stimulus suppression, cognitive impairment). Here a novel measure for quantifying articulation effort is introduced, and when applied experimentally to the DAIC corpus shows promise for identifying speech data that are more discriminative of depression. Interestingly, experiment results demonstrate that by selecting speech with higher articulation effort, linguistic complexity, or word-based arousal/valence, improvements in acoustic speech-based feature depression classification performance can be achieved, serving as a guide for future elicitation design.",
keywords = "Affect, Computational paralinguistics, Depression classification, Sentiment, Speech production",
author = "Brian Stasak and Julien Epps and Roland Goecke",
year = "2017",
month = "8",
day = "20",
doi = "10.21437/Interspeech.2017-1223",
language = "English",
series = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",
publisher = "International Speech Communication Association (ISCA)",
pages = "834--838",
booktitle = "Proceedings of Interspeech 2017",

}

Stasak, B, Epps, J & Goecke, R 2017, Elicitation design for acoustic depression classification: An investigation of articulation effort, linguistic complexity, and word affect. in Proceedings of Interspeech 2017. Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, International Speech Communication Association (ISCA), Stockholm, Sweden, pp. 834-838, 18th Annual Conference of the International Speech Communication Association, INTERSPEECH 2017, Stockholm, Sweden, 20/08/17. https://doi.org/10.21437/Interspeech.2017-1223

Elicitation design for acoustic depression classification: An investigation of articulation effort, linguistic complexity, and word affect. / Stasak, Brian; Epps, Julien; Goecke, Roland.

Proceedings of Interspeech 2017. Stockholm, Sweden : International Speech Communication Association (ISCA), 2017. p. 834-838 (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH).

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Elicitation design for acoustic depression classification: An investigation of articulation effort, linguistic complexity, and word affect

AU - Stasak, Brian

AU - Epps, Julien

AU - Goecke, Roland

PY - 2017/8/20

Y1 - 2017/8/20

N2 - Assessment of neurological and psychiatric disorders like depression are unusual from a speech processing perspective, in that speakers can be prompted or instructed in what they should say (e.g. as part of a clinical assessment). Despite prior speech-based depression studies that have used a variety of speech elicitation methods, there has been little evaluation of the best elicitation mode. One approach to understand this better is to analyze an existing database from the perspective of articulation effort, word affect, and linguistic complexity measures as proxies for depression sub-symptoms (e.g. psychomotor retardation, negative stimulus suppression, cognitive impairment). Here a novel measure for quantifying articulation effort is introduced, and when applied experimentally to the DAIC corpus shows promise for identifying speech data that are more discriminative of depression. Interestingly, experiment results demonstrate that by selecting speech with higher articulation effort, linguistic complexity, or word-based arousal/valence, improvements in acoustic speech-based feature depression classification performance can be achieved, serving as a guide for future elicitation design.

AB - Assessment of neurological and psychiatric disorders like depression are unusual from a speech processing perspective, in that speakers can be prompted or instructed in what they should say (e.g. as part of a clinical assessment). Despite prior speech-based depression studies that have used a variety of speech elicitation methods, there has been little evaluation of the best elicitation mode. One approach to understand this better is to analyze an existing database from the perspective of articulation effort, word affect, and linguistic complexity measures as proxies for depression sub-symptoms (e.g. psychomotor retardation, negative stimulus suppression, cognitive impairment). Here a novel measure for quantifying articulation effort is introduced, and when applied experimentally to the DAIC corpus shows promise for identifying speech data that are more discriminative of depression. Interestingly, experiment results demonstrate that by selecting speech with higher articulation effort, linguistic complexity, or word-based arousal/valence, improvements in acoustic speech-based feature depression classification performance can be achieved, serving as a guide for future elicitation design.

KW - Affect

KW - Computational paralinguistics

KW - Depression classification

KW - Sentiment

KW - Speech production

UR - http://www.scopus.com/inward/record.url?scp=85035328159&partnerID=8YFLogxK

U2 - 10.21437/Interspeech.2017-1223

DO - 10.21437/Interspeech.2017-1223

M3 - Conference contribution

T3 - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

SP - 834

EP - 838

BT - Proceedings of Interspeech 2017

PB - International Speech Communication Association (ISCA)

CY - Stockholm, Sweden

ER -

Stasak B, Epps J, Goecke R. Elicitation design for acoustic depression classification: An investigation of articulation effort, linguistic complexity, and word affect. In Proceedings of Interspeech 2017. Stockholm, Sweden: International Speech Communication Association (ISCA). 2017. p. 834-838. (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH). https://doi.org/10.21437/Interspeech.2017-1223