TY - GEN
T1 - Diagnosis of depression by behavioural signals
T2 - 3rd ACM International Workshop on Audio/Visual Emotion Challenge, AVEC 2013
AU - Cummins, Nicholas
AU - Joshi, Jyoti
AU - Dhall, Abhinav
AU - Sethu, Vidhyasaharan
AU - Goecke, Roland
AU - Epps, Julien
PY - 2013
Y1 - 2013
N2 - Quantifying behavioural changes in depression using affective computing techniques is the first step in developing an objective diagnostic aid, with clinical utility, for clinical depression. As part of the AVEC 2013 Challenge, we present a multimodal approach for the Depression Sub-Challenge using a GMM-UBM system with three different kernels for the audio subsystem and Space Time Interest Points in a Bag-of-Words approach for the vision subsystem. These are then fused at the feature level to form the combined AV system. Key results include the strong performance of acoustic audio features and the bag-of-words visual features in predicting an individual's level of depression using regression. Interestingly, in the context of the small amount of literature on the subject, is that our feature level multimodal fusion technique is able to outperform both the audio and visual challenge baselines. ©
AB - Quantifying behavioural changes in depression using affective computing techniques is the first step in developing an objective diagnostic aid, with clinical utility, for clinical depression. As part of the AVEC 2013 Challenge, we present a multimodal approach for the Depression Sub-Challenge using a GMM-UBM system with three different kernels for the audio subsystem and Space Time Interest Points in a Bag-of-Words approach for the vision subsystem. These are then fused at the feature level to form the combined AV system. Key results include the strong performance of acoustic audio features and the bag-of-words visual features in predicting an individual's level of depression using regression. Interestingly, in the context of the small amount of literature on the subject, is that our feature level multimodal fusion technique is able to outperform both the audio and visual challenge baselines. ©
KW - Acoustic speech features
KW - Bag-of-words
KW - Behavioural signals
KW - Depression
KW - Multimodal fusion
KW - Multimodal technologies
KW - Pyramid of histogram of gradients
KW - Space-time interest points
KW - Support vector regression
UR - http://www.scopus.com/inward/record.url?scp=84887498641&partnerID=8YFLogxK
U2 - 10.1145/2512530.2512535
DO - 10.1145/2512530.2512535
M3 - Conference contribution
SN - 9781450323956
T3 - AVEC 2013 - Proceedings of the 3rd ACM International Workshop on Audio/Visual Emotion Challenge
SP - 11
EP - 20
BT - AVEC 2013 - Proceedings of the 3rd ACM International Workshop on Audio/Visual Emotion Challenge
PB - Association for Computing Machinery
Y2 - 21 October 2013 through 21 October 2013
ER -