5 Hits in 4.2 sec

Multimodal and Multiresolution Depression Detection from Speech and Facial Landmark Features

Md Nasir, Arindam Jati, Prashanth Gurunath Shivakumar, Sandeep Nallan Chakravarthula, Panayiotis Georgiou
2016 Proceedings of the 6th International Workshop on Audio/Visual Emotion Challenge - AVEC '16  
Keywords Multimodal signal processing, behavioral signal processing (BSP), depression, Teager energy operator, i-vector, facial landmark, fusion  ...  On the other hand, polynomial parameterization of facial landmark features achieves the best performance among all systems and outperforms the best baseline system as well.  ...  Our hypothesis is that these features capture information about facial expressions relevant to depression detection. 11 distance features and 26 area features are extracted from the x and y co-ordinates  ... 
doi:10.1145/2988257.2988261 dblp:conf/mm/NasirJSCG16 fatcat:33geyegcgfcclgnmufbc5f32iq

Toward an affect-sensitive multimodal human-computer interaction

M. Pantic, L.J.M. Rothkrantz
2003 Proceedings of the IEEE  
Affective arousal modulates all nonverbal communicative cues (facial expressions, body movements, and vocal and physiological reactions).  ...  In a face-to-face interaction, humans detect and interpret those interactive signals of their communicator with little or no effort.  ...  Koppelaar, and anonymous reviewers for their helpful comments and suggestions.  ... 
doi:10.1109/jproc.2003.817122 fatcat:a2mq7h2lwzepnjexicqr3spc2m

On the relations among temporal integration for loudness, loudness discrimination, and the form of the loudness function

So/ren Buus, Mary Florentine, Torben Poulsen
1996 Journal of the Acoustical Society of America  
Chemical impairment measure (CMI) based on speech was used by the author to detect and measure the physiological/neurological depression. CMI ranges front zero to three on a special scale.  ...  The results indicate a trade-off between efficiency and multimode excitation, as expected.  ...  When speech rate (fast and slow) was manipulated, the VCVs were from sentences with stress on the VCV only.  ... 
doi:10.1121/1.415616 fatcat:o3peikxywvgrtccqqlvwx55j3y

Wavelet-based Recognition of Facial Expressions and Faces [article]

Ahmad Poursaberi, University Of Calgary, University Of Calgary, Svetlana Yanushkevich, Marina Gavrilova
This research proposes a facial biometric analysis using a new facial feature detection based on a modified Frangi filter.  ...  The joint FR/FER uses new feature extraction technique called Gauss-Laguerre wavelets, which provides rich and unique features suitable for expressions classification and identity recognition.  ...  In this case, the facial points detection has been removed from the process, and the global facial features have been used.  ... 
doi:10.11575/prism/28676 fatcat:fxz5iwo4mzgi7ksjvqeqiqesx4

CENTRIC 2013 Technical Program Committee

Stephan Böhm, Stephan Böhm, Mario Hoffmann, Guadalupe Ortiz, Rainer Falk, Siemens Ag -München, Juong-Sik Deutschland, Lee, Stephan Böhm, Mario Hoffmann, Guadalupe Ortiz, Rainer Falk (+38 others)
The human-oriented and personalized technologies and services rely on a key set of features, some to be deployed, others getting more mature (personal profiles, preferences, identity, proximity, personal  ...  Following, advanced applications covering human related activities benefit from personalized and human-oriented networks and services, especially preventive and personalized medicine, body networks and  ...  ISBN: 978-1-61208-306-3 CENTRIC 2013 : The Sixth International Conference on Advances in Human-oriented and Personalized Mechanisms, Technologies, and Services The Case for Integrating Needs and Preferences  ...