Moving Fast and Slow: Analysis of Representations and Post-Processing in Speech-Driven Automatic Gesture Generation

Moving Fast and Slow : Analysis of Representations and Post-Processing in Speech-Driven Automatic Gesture Generation

Kucherenko, Taras, 1994- (författare): KTH,Robotik, perception och lärande, RPL

Hasegawa, Dai (författare)

Kaneko, Naoshi (författare)

Henter, Gustav Eje, Assistant Professor (författare): KTH,Robotik, perception och lärande, RPL

Kjellström, Hedvig, 1973- (författare): KTH,Robotik, perception och lärande, RPL

(creator_code:org_t)

2021-02-17
2021
Engelska.
Ingår i: International Journal of Human-Computer Interaction. - : Informa UK Limited. - 1044-7318 .- 1532-7590. ; 37:14, s. 1300-1316

Relaterad länk:: https://doi.org/10.1...; visa fler...; https://www.tandfonl...; https://urn.kb.se/re...; https://doi.org/10.1...; visa färre...

Abstract Ämnesord

Stäng

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.

Av författaren/redakt...: Kucherenko, Tara ...; Hasegawa, Dai; Kaneko, Naoshi; Henter, Gustav E ...; Kjellström, Hedv ...

Om ämnet

NATURVETENSKAP: NATURVETENSKAP; och Data och informa ...; och Människa datorin ...

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.