Automatic annotation of gestural units in spontaneous face-to-face interaction
2016 (English)In: MA3HMI 2016 - Proceedings of the Workshop on Multimodal Analyses Enabling Artificial Agents in Human-Machine Interaction, 2016, 15-19 p.Conference paper (Refereed)
Speech and gesture co-occur in spontaneous dialogue in a highly complex fashion. There is a large variability in the motion that people exhibit during a dialogue, and different kinds of motion occur during different states of the interaction. A wide range of multimodal interface applications, for example in the fields of virtual agents or social robots, can be envisioned where it is important to be able to automatically identify gestures that carry information and discriminate them from other types of motion. While it is easy for a human to distinguish and segment manual gestures from a flow of multimodal information, the same task is not trivial to perform for a machine. In this paper we present a method to automatically segment and label gestural units from a stream of 3D motion capture data. The gestural flow is modeled with a 2-level Hierarchical Hidden Markov Model (HHMM) where the sub-states correspond to gesture phases. The model is trained based on labels of complete gesture units and self-adaptive manipulators. The model is tested and validated on two datasets differing in genre and in method of capturing motion, and outperforms a state-of-the-art SVM classifier on a publicly available dataset.
Place, publisher, year, edition, pages
2016. 15-19 p.
Gesture recognition, Motion capture, Spontaneous dialogue, Hidden Markov models, Man machine systems, Markov processes, Online systems, 3D motion capture, Automatic annotation, Face-to-face interaction, Hierarchical hidden markov models, Multi-modal information, Multi-modal interfaces, Classification (of information)
IdentifiersURN: urn:nbn:se:kth:diva-202135DOI: 10.1145/3011263.3011268ScopusID: 2-s2.0-85003571594ISBN: 9781450345620 OAI: oai:DiVA.org:kth-202135DiVA: diva2:1081313
2016 Workshop on Multimodal Analyses Enabling Artificial Agents in Human-Machine Interaction, MA3HMI 2016, 12 November 2016 through 16 November 2016
FunderSwedish Research Council, 2010-4646
Funding text: The work reported here is carried out within the projects: "Timing of intonation and gestures in spoken communication," (P12-0634:1) funded by the Bank of Sweden Tercentenary Foundation, and "Large-scale massively multimodal modelling of non-verbal behaviour in spontaneous dialogue," (VR 2010-4646) funded by Swedish Research Council.2017-03-132017-03-132017-03-13Bibliographically approved