Modeling naturalistic affective states via facial and vocal expressions recognition

Caridakis, G; Malatesta, L; Kessous, L; Amir, N; Raouzaiou, A; Karpouzis, K

dc.contributor.author	Caridakis, G	en
dc.contributor.author	Malatesta, L	en
dc.contributor.author	Kessous, L	en
dc.contributor.author	Amir, N	en
dc.contributor.author	Raouzaiou, A	en
dc.contributor.author	Karpouzis, K	en
dc.date.accessioned	2014-03-01T02:44:06Z
dc.date.available	2014-03-01T02:44:06Z
dc.date.issued	2006	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31678
dc.subject	Affective interaction	en
dc.subject	Facial expression recognition	en
dc.subject	Image processing	en
dc.subject	Multimodal analysis	en
dc.subject	Naturalistic data	en
dc.subject	Prosodic feature extraction	en
dc.subject	User modeling	en
dc.subject.other	Artificial intelligence	en
dc.subject.other	Computer simulation languages	en
dc.subject.other	Feedback	en
dc.subject.other	Image recognition	en
dc.subject.other	Speech recognition	en
dc.subject.other	User interfaces	en
dc.subject.other	Affective states	en
dc.subject.other	Audiovisual material	en
dc.subject.other	Facial expressions recognition	en
dc.subject.other	Vocal expressions recognition	en
dc.subject.other	Human computer interaction	en
dc.title	Modeling naturalistic affective states via facial and vocal expressions recognition	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1145/1180995.1181029	en
heal.identifier.secondary	http://dx.doi.org/10.1145/1180995.1181029	en
heal.publicationDate	2006	en
heal.abstract	Affective and human-centered computing are two areas related to HCI which have attracted attention during the past years. One of the reasons that this may be attributed to, is the plethora of devices able to record and process multimodal input from the part of the users and adapt their functionality to their preferences or individual habits, thus enhancing usability and becoming attractive to users less accustomed with conventional interfaces. In the quest to receive feedback from the users in an unobtrusive manner, the visual and auditory modalities allow us to infer the users' emotional state, combining information both from facial expression recognition and speech prosody feature extraction. In this paper, we describe a multi-cue, dynamic approach in naturalistic video sequences. Contrary to strictly controlled recording conditions of audiovisual material, the current research focuses on sequences taken from nearly real world situations. Recognition is performed via a 'Simple Recurrent Network' which lends itself well to modeling dynamic events in both user's facial expressions and speech. Moreover this approach differs from existing work in that it models user expressivity using a dimensional representation of activation and valence, instead of detecting the usual 'universal emotions' which are scarce in everyday human-machine interaction. The algorithm is deployed on an audiovisual database which was recorded simulating human-human discourse and, therefore, contains less extreme expressivity and subtle variations of a number of emotion labels. Copyright 2006 ACM.	en
heal.journalName	ICMI'06: 8th International Conference on Multimodal Interfaces, Conference Proceeding	en
dc.identifier.doi	10.1145/1180995.1181029	en
dc.identifier.spage	146	en
dc.identifier.epage	154	en