Sökning: L773:1044 7318 OR L773:1532 7590 >
Moving Fast and Slow :
-
Kucherenko, Taras,1994-KTH,Robotik, perception och lärande, RPL
(författare)
Moving Fast and Slow : Analysis of Representations and Post-Processing in Speech-Driven Automatic Gesture Generation
- Artikel/kapitelEngelska2021
Förlag, utgivningsår, omfång ...
-
2021-02-17
-
Informa UK Limited,2021
-
printrdacarrier
Nummerbeteckningar
-
LIBRIS-ID:oai:DiVA.org:kth-290787
-
https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-290787URI
-
https://doi.org/10.1080/10447318.2021.1883883DOI
Kompletterande språkuppgifter
-
Språk:engelska
-
Sammanfattning på:engelska
Ingår i deldatabas
Klassifikation
-
Ämneskategori:ref swepub-contenttype
-
Ämneskategori:art swepub-publicationtype
Anmärkningar
-
QC 20211109
-
This paper presents a novel framework for speech-driven gesture production, applicable to virtual agents to enhance human-computer interaction. Specifically, we extend recent deep-learning-based, data-driven methods for speech-driven gesture generation by incorporating representation learning. Our model takes speech as input and produces gestures as output, in the form of a sequence of 3D coordinates. We provide an analysis of different representations for the input (speech) and the output (motion) of the network by both objective and subjective evaluations. We also analyze the importance of smoothing of the produced motion. Our results indicated that the proposed method improved on our baseline in terms of objective measures. For example, it better captured the motion dynamics and better matched the motion-speed distribution. Moreover, we performed user studies on two different datasets. The studies confirmed that our proposed method is perceived as more natural than the baseline, although the difference in the studies was eliminated by appropriate post-processing: hip-centering and smoothing. We conclude that it is important to take both motion representation and post-processing into account when designing an automatic gesture-production method.
Ämnesord och genrebeteckningar
Biuppslag (personer, institutioner, konferenser, titlar ...)
-
Hasegawa, Dai
(författare)
-
Kaneko, Naoshi
(författare)
-
Henter, Gustav Eje,Assistant ProfessorKTH,Robotik, perception och lärande, RPL(Swepub:kth)u1cj22n0
(författare)
-
Kjellström, Hedvig,1973-KTH,Robotik, perception och lärande, RPL(Swepub:kth)u1izkbhh
(författare)
-
KTHRobotik, perception och lärande, RPL
(creator_code:org_t)
Sammanhörande titlar
-
Ingår i:International Journal of Human-Computer Interaction: Informa UK Limited37:14, s. 1300-13161044-73181532-7590
Internetlänk
Hitta via bibliotek
Till lärosätets databas