TY - GEN
T1 - Depression severity estimation from multiple modalities
AU - Stepanov, Evgeny A.
AU - Lathuiliere, Stephane
AU - Chowdhury, Shammur Absar
AU - Ghosh, Arindam
AU - Vieriu, Radu Laurentiu
AU - Sebe, Nicu
AU - Riccardi, Giuseppe
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/11/9
Y1 - 2018/11/9
N2 - Depression is a major debilitating disorder which can affect people from all ages. With a continuous increase in the number of annual cases of depression, there is a need to develop automatic techniques for the detection of the presence and its severity. We explore different modalities (speech, behavioral characteristics, language and visual features extracted from face) to design and develop automatic methods for the detection of depression. In psychology literature, the eight-item Patient Health Questionnaire depression scale (PHQ-8) is well established as a tool for measuring the severity of depression. In this paper we aim to automatically predict the total sum of PHQ-8 scores from features extracted from the different modalities. We demonstrate that among the considered modalities, behavioral characteristic features extracted from speech yield the lowest MAE, outperforming the best system at the Audio/Visual Emotion Challenge (AVEC) 2017 depression sub-challenge.
AB - Depression is a major debilitating disorder which can affect people from all ages. With a continuous increase in the number of annual cases of depression, there is a need to develop automatic techniques for the detection of the presence and its severity. We explore different modalities (speech, behavioral characteristics, language and visual features extracted from face) to design and develop automatic methods for the detection of depression. In psychology literature, the eight-item Patient Health Questionnaire depression scale (PHQ-8) is well established as a tool for measuring the severity of depression. In this paper we aim to automatically predict the total sum of PHQ-8 scores from features extracted from the different modalities. We demonstrate that among the considered modalities, behavioral characteristic features extracted from speech yield the lowest MAE, outperforming the best system at the Audio/Visual Emotion Challenge (AVEC) 2017 depression sub-challenge.
KW - Affective Computing
KW - Depression Detection
KW - Facial Expressions
KW - Machine Learning
KW - Natural Language Processing
KW - Speech
UR - http://www.scopus.com/inward/record.url?scp=85058347348&partnerID=8YFLogxK
U2 - 10.1109/HealthCom.2018.8531119
DO - 10.1109/HealthCom.2018.8531119
M3 - Conference contribution
AN - SCOPUS:85058347348
T3 - 2018 IEEE 20th International Conference on e-Health Networking, Applications and Services, Healthcom 2018
BT - 2018 IEEE 20th International Conference on e-Health Networking, Applications and Services, Healthcom 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 20th IEEE International Conference on e-Health Networking, Applications and Services, Healthcom 2018
Y2 - 17 September 2018 through 20 September 2018
ER -