Multimodal models for contextual affect assessment in real-time
dc.contributor.author | Vice, J. | |
dc.contributor.author | Khan, Masood | |
dc.contributor.author | Yanushkevich, S. | |
dc.date.accessioned | 2020-07-31T08:05:39Z | |
dc.date.available | 2020-07-31T08:05:39Z | |
dc.date.issued | 2019 | |
dc.identifier.citation | Vice, J. and Khan, M.M. and Yanushkevich, S. 2019. Multimodal models for contextual affect assessment in real-time, in Proceedings of the 2019 IEEE First International Conference on Cognitive Machine Intelligence (CogMI), Dec 12-14 2019. Los Angeles, USA: IEEE. | |
dc.identifier.uri | http://hdl.handle.net/20.500.11937/80264 | |
dc.identifier.doi | 10.1109/CogMI48466.2019.00020 | |
dc.description.abstract |
Most affect classification schemes rely on near accurate single-cue models resulting in less than required accuracy under certain peculiar conditions. We investigate how the holism of a multimodal solution could be exploited for affect classification. This paper presents the design and implementation of a prototype, stand-alone, real-time multimodal affective state classification system. The presented system utilizes speech and facial muscle movements to create a holistic classifier. The system combines a facial expression classifier and a speech classifier that analyses speech through paralanguage and propositional content. The proposed classification scheme includes a Support Vector Machine (SVM) - paralanguage; a K-Nearest Neighbor (KNN) - propositional content and an InceptionV3 neural network - facial expressions of affective states. The SVM and Inception models boasted respective validation accuracies of 99.2% and 92.78%. | |
dc.title | Multimodal models for contextual affect assessment in real-time | |
dc.type | Conference Paper | |
dcterms.source.startPage | 87 | |
dcterms.source.endPage | 92 | |
dcterms.source.title | Proceedings - 2019 IEEE 1st International Conference on Cognitive Machine Intelligence, CogMI 2019 | |
dcterms.source.isbn | 9781728167374 | |
dc.date.updated | 2020-07-31T08:05:39Z | |
curtin.department | School of Civil and Mechanical Engineering | |
curtin.accessStatus | Fulltext not available | |
curtin.faculty | Faculty of Science and Engineering | |
curtin.contributor.orcid | Khan, Masood [0000-0002-2769-2380] | |
curtin.contributor.scopusauthorid | Khan, Masood [7410317782] |
Files in this item
Files | Size | Format | View |
---|---|---|---|
There are no files associated with this item. |