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
KW - sentiment
KW - computational paralinguistics
KW - depression classification
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
AN - SCOPUS:85035328159
VL - 1-6
T3 - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
SP - 834
EP - 838
BT - 18th Annual Conference of the International Speech Communication Association (INTERSPEECH 2017)
PB - International Speech Communication Association (ISCA)
CY - Stockholm, Sweden
T2 - 18th Annual Conference of the International Speech Communication Association, INTERSPEECH 2017
Y2 - 20 August 2017 through 24 August 2017
ER -