Sökning: onr:"swepub:oai:DiVA.org:kth-290787" > Moving Fast and Slow :
Fältnamn | Indikatorer | Metadata |
---|---|---|
000 | 03489naa a2200493 4500 | |
001 | oai:DiVA.org:kth-290787 | |
003 | SwePub | |
008 | 210222s2021 | |||||||||||000 ||eng| | |
024 | 7 | a https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-2907872 URI |
024 | 7 | a https://doi.org/10.1080/10447318.2021.18838832 DOI |
040 | a (SwePub)kth | |
041 | a engb eng | |
042 | 9 SwePub | |
072 | 7 | a ref2 swepub-contenttype |
072 | 7 | a art2 swepub-publicationtype |
100 | 1 | a Kucherenko, Taras,d 1994-u KTH,Robotik, perception och lärande, RPL4 aut0 (Swepub:kth)u1igz10x |
245 | 1 0 | a Moving Fast and Slow :b Analysis of Representations and Post-Processing in Speech-Driven Automatic Gesture Generation |
264 | c 2021-02-17 | |
264 | 1 | b Informa UK Limited,c 2021 |
338 | a print2 rdacarrier | |
500 | a QC 20211109 | |
520 | a 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. | |
650 | 7 | a NATURVETENSKAPx Data- och informationsvetenskapx Människa-datorinteraktion0 (SwePub)102042 hsv//swe |
650 | 7 | a NATURAL SCIENCESx Computer and Information Sciencesx Human Computer Interaction0 (SwePub)102042 hsv//eng |
653 | a Gesture generation | |
653 | a representation learning | |
653 | a neural network | |
653 | a deep learning | |
653 | a virtual agents | |
653 | a non-verbal behavior | |
653 | a Computer Science | |
653 | a Datalogi | |
653 | a Computer Science | |
653 | a Datalogi | |
700 | 1 | a Hasegawa, Dai4 aut |
700 | 1 | a Kaneko, Naoshi4 aut |
700 | 1 | a Henter, Gustav Eje,c Assistant Professoru KTH,Robotik, perception och lärande, RPL4 aut0 (Swepub:kth)u1cj22n0 |
700 | 1 | a Kjellström, Hedvig,d 1973-u KTH,Robotik, perception och lärande, RPL4 aut0 (Swepub:kth)u1izkbhh |
710 | 2 | a KTHb Robotik, perception och lärande, RPL4 org |
773 | 0 | t International Journal of Human-Computer Interactiond : Informa UK Limitedg 37:14, s. 1300-1316q 37:14<1300-1316x 1044-7318x 1532-7590 |
856 | 4 | u https://doi.org/10.1080/10447318.2021.1883883y Fulltext |
856 | 4 | u https://www.tandfonline.com/doi/pdf/10.1080/10447318.2021.1883883?needAccess=true |
856 | 4 8 | u https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-290787 |
856 | 4 8 | u https://doi.org/10.1080/10447318.2021.1883883 |
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.
Kopiera och spara länken för att återkomma till aktuell vy