Converting emotional voice to motion for robot telepresence

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

In this paper we present a new method for producing affective motion for humanoid robots. The NAO robot, like other humanoids, does not possess facial features to convey emotion. Instead, our proposed system generates pose-independent robot movement using a description of emotion through speed, intensity, regularity and extent (DESIRE). We show how the DESIRE framework can link the emotional content of voice and gesture, without the need for an emotion recognition system. Our results show that DESIRE movement can be used to effectively convey at least four emotions with user agreement 60-75%, and that voices converted to motion through SIRE maintained the same emotion significantly higher than chance, even across cultures (German to Japanese). Additionally, portrayals recognized as happiness were rated significantly easier to understand with motion over voice alone.

Original languageEnglish
Title of host publicationIEEE-RAS International Conference on Humanoid Robots
Pages472-479
Number of pages8
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event2011 11th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS 2011 - Bled
Duration: 2011 Oct 262011 Oct 28

Other

Other2011 11th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS 2011
CityBled
Period11/10/2611/10/28

Fingerprint

Robots

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Human-Computer Interaction
  • Electrical and Electronic Engineering

Cite this

Lim, A., Ogata, T., & Okuno, H. G. (2011). Converting emotional voice to motion for robot telepresence. In IEEE-RAS International Conference on Humanoid Robots (pp. 472-479). [6100891] https://doi.org/10.1109/Humanoids.2011.6100891

Converting emotional voice to motion for robot telepresence. / Lim, Angelica; Ogata, Tetsuya; Okuno, Hiroshi G.

IEEE-RAS International Conference on Humanoid Robots. 2011. p. 472-479 6100891.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Lim, A, Ogata, T & Okuno, HG 2011, Converting emotional voice to motion for robot telepresence. in IEEE-RAS International Conference on Humanoid Robots., 6100891, pp. 472-479, 2011 11th IEEE-RAS International Conference on Humanoid Robots, HUMANOIDS 2011, Bled, 11/10/26. https://doi.org/10.1109/Humanoids.2011.6100891
Lim A, Ogata T, Okuno HG. Converting emotional voice to motion for robot telepresence. In IEEE-RAS International Conference on Humanoid Robots. 2011. p. 472-479. 6100891 https://doi.org/10.1109/Humanoids.2011.6100891
Lim, Angelica ; Ogata, Tetsuya ; Okuno, Hiroshi G. / Converting emotional voice to motion for robot telepresence. IEEE-RAS International Conference on Humanoid Robots. 2011. pp. 472-479
@inproceedings{993c006f064049ad8cd1bf00a09f65f4,
title = "Converting emotional voice to motion for robot telepresence",
abstract = "In this paper we present a new method for producing affective motion for humanoid robots. The NAO robot, like other humanoids, does not possess facial features to convey emotion. Instead, our proposed system generates pose-independent robot movement using a description of emotion through speed, intensity, regularity and extent (DESIRE). We show how the DESIRE framework can link the emotional content of voice and gesture, without the need for an emotion recognition system. Our results show that DESIRE movement can be used to effectively convey at least four emotions with user agreement 60-75{\%}, and that voices converted to motion through SIRE maintained the same emotion significantly higher than chance, even across cultures (German to Japanese). Additionally, portrayals recognized as happiness were rated significantly easier to understand with motion over voice alone.",
author = "Angelica Lim and Tetsuya Ogata and Okuno, {Hiroshi G.}",
year = "2011",
doi = "10.1109/Humanoids.2011.6100891",
language = "English",
isbn = "9781612848679",
pages = "472--479",
booktitle = "IEEE-RAS International Conference on Humanoid Robots",

}

TY - GEN

T1 - Converting emotional voice to motion for robot telepresence

AU - Lim, Angelica

AU - Ogata, Tetsuya

AU - Okuno, Hiroshi G.

PY - 2011

Y1 - 2011

N2 - In this paper we present a new method for producing affective motion for humanoid robots. The NAO robot, like other humanoids, does not possess facial features to convey emotion. Instead, our proposed system generates pose-independent robot movement using a description of emotion through speed, intensity, regularity and extent (DESIRE). We show how the DESIRE framework can link the emotional content of voice and gesture, without the need for an emotion recognition system. Our results show that DESIRE movement can be used to effectively convey at least four emotions with user agreement 60-75%, and that voices converted to motion through SIRE maintained the same emotion significantly higher than chance, even across cultures (German to Japanese). Additionally, portrayals recognized as happiness were rated significantly easier to understand with motion over voice alone.

AB - In this paper we present a new method for producing affective motion for humanoid robots. The NAO robot, like other humanoids, does not possess facial features to convey emotion. Instead, our proposed system generates pose-independent robot movement using a description of emotion through speed, intensity, regularity and extent (DESIRE). We show how the DESIRE framework can link the emotional content of voice and gesture, without the need for an emotion recognition system. Our results show that DESIRE movement can be used to effectively convey at least four emotions with user agreement 60-75%, and that voices converted to motion through SIRE maintained the same emotion significantly higher than chance, even across cultures (German to Japanese). Additionally, portrayals recognized as happiness were rated significantly easier to understand with motion over voice alone.

UR - http://www.scopus.com/inward/record.url?scp=84856341339&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84856341339&partnerID=8YFLogxK

U2 - 10.1109/Humanoids.2011.6100891

DO - 10.1109/Humanoids.2011.6100891

M3 - Conference contribution

SN - 9781612848679

SP - 472

EP - 479

BT - IEEE-RAS International Conference on Humanoid Robots

ER -