Automatic recognition of gesture qualities in speech delivery in VR - work-in-progress

StatusVoR
Dublin Core metadata
Alternative title
Authors
Skrzek, Tomasz
Malawski, Filip
Tadeja, Sławomir K.
Hekiert-Małozięć, Daniela
Hemmerling, Daria
Igras-Cybulska, Magdalena
Monograph
2024 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW)
Monograph (alternative title)
Editor
Date
2024-05-29
Place of publication
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Journal title
Volume
Pages
624-627
DOI
ISSN
ISBN
9798350374490
eISBN
Series
Series number
ISSN of series
Weblink
https://www.computer.org/csdl/proceedings-article/vrw/2024/744900a624/1Xlc1zuAk8w
Access date
2024-06-05
Remarks
Abstract PL
Abstract EN
Gesture use during public speaking can be analyzed as an aspect of speaker performance as well as an indicator of speaker emotions. Recognizing gesture quality rather than identifying specific gestures presents an underexplored challenge compared to traditional gesture recognition in virtual reality (VR). To that end, we use a VR headset and controllers to create a database of 162 five-second-long gestures. Next, we ask ten judges to evaluate the quality of gestures in three dimensions, i.e., dynamics, range, and between-hand distance, on a low-medium-high scale with average Fleiss Kappa 0.39 inter-rater agreement. A comparison of various classifiers revealed that the Support Vector Machine (SVM) yielded the best results, achieving classification accuracy of 70-85% for each quality dimension.
Abstract other
Keywords PL
Keywords EN
Keywords other
Conference edition name
2024 IEEE Conference on Virtual Reality and 3D User Interfaces
Conference place
Orlando
Start date
2024-03-16
Finish date
2024-03
Exhibition title
Place of exhibition (institution)
Exhibition curator
Organisational Unit
Wydział Psychologii w Warszawie
Instytut Psychologii
Wydział Nauk Humanistycznych w Warszawie
URI
https://share.swps.edu.pl/handle/swps/702
Type
Version
Version of Record
License type
closedaccess
There is no access to this item
Funder
Time range from
Time range to
Contact person name
item.page.relation.dataset
Related publication
Related publication
Grant/project name
Views
Views13
Acquisition Date4.04.2025
Downloads
Downloads2
Acquisition Date4.04.2025