Switching Wizard of Oz for the online evaluation of backchannel behavior

Ronald Walter Poppe, Mark ter Maat, Dirk K.J. Heylen

Research output: Contribution to journalArticleAcademicpeer-review

2 Citations (Scopus)

Abstract

The Switching Wizard of Oz (SWOZ) is a setup to evaluate human behavior synthesis algorithms in online face-to-face interactions. Conversational partners are represented to each other as virtual agents, whose animated behavior is either based on a synthesis algorithm, or driven by the actual behavior of the conversational partner. Human and algorithm have the same expression capabilities. The source is switched at random intervals, which means that the algorithm’s behavior can only be identified when it deviates from what is regarded as appropriate. The SWOZ approach is especially suitable for the controlled evaluation of synthesis algorithms that consider a limited set of behaviors. We evaluate a backchannel synthesis algorithm for speaker–listener dialogs using an asymmetric version of the framework. Human speakers talk to virtual listeners, that are either controlled by human listeners or by an algorithm. Speakers indicate when they feel they are no longer talking to a human listener. Analysis of these responses reveals patterns of inappropriate behavior in terms of quantity and timing of backchannels. These insights can be used to improve synthesis algorithms.
Original languageUndefined
Pages (from-to)109-117
Number of pages9
JournalJournal on multimodal user interfaces
Volume8
Issue number1
DOIs
Publication statusPublished - Mar 2014

Keywords

  • EWI-24794
  • HMI-IA: Intelligent Agents
  • User study
  • Perception
  • IR-91465
  • Listening Behavior
  • Wizard of Oz
  • METIS-305901
  • Backchannels

Cite this

@article{bcb3a079930142e299ccaba7686c04b9,
title = "Switching Wizard of Oz for the online evaluation of backchannel behavior",
abstract = "The Switching Wizard of Oz (SWOZ) is a setup to evaluate human behavior synthesis algorithms in online face-to-face interactions. Conversational partners are represented to each other as virtual agents, whose animated behavior is either based on a synthesis algorithm, or driven by the actual behavior of the conversational partner. Human and algorithm have the same expression capabilities. The source is switched at random intervals, which means that the algorithm’s behavior can only be identified when it deviates from what is regarded as appropriate. The SWOZ approach is especially suitable for the controlled evaluation of synthesis algorithms that consider a limited set of behaviors. We evaluate a backchannel synthesis algorithm for speaker–listener dialogs using an asymmetric version of the framework. Human speakers talk to virtual listeners, that are either controlled by human listeners or by an algorithm. Speakers indicate when they feel they are no longer talking to a human listener. Analysis of these responses reveals patterns of inappropriate behavior in terms of quantity and timing of backchannels. These insights can be used to improve synthesis algorithms.",
keywords = "EWI-24794, HMI-IA: Intelligent Agents, User study, Perception, IR-91465, Listening Behavior, Wizard of Oz, METIS-305901, Backchannels",
author = "Poppe, {Ronald Walter} and {ter Maat}, Mark and Heylen, {Dirk K.J.}",
note = "eemcs-eprint-24794",
year = "2014",
month = "3",
doi = "10.1007/s12193-013-0131-2",
language = "Undefined",
volume = "8",
pages = "109--117",
journal = "Journal on multimodal user interfaces",
issn = "1783-7677",
publisher = "Springer",
number = "1",

}

Switching Wizard of Oz for the online evaluation of backchannel behavior. / Poppe, Ronald Walter; ter Maat, Mark; Heylen, Dirk K.J.

In: Journal on multimodal user interfaces, Vol. 8, No. 1, 03.2014, p. 109-117.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Switching Wizard of Oz for the online evaluation of backchannel behavior

AU - Poppe, Ronald Walter

AU - ter Maat, Mark

AU - Heylen, Dirk K.J.

N1 - eemcs-eprint-24794

PY - 2014/3

Y1 - 2014/3

N2 - The Switching Wizard of Oz (SWOZ) is a setup to evaluate human behavior synthesis algorithms in online face-to-face interactions. Conversational partners are represented to each other as virtual agents, whose animated behavior is either based on a synthesis algorithm, or driven by the actual behavior of the conversational partner. Human and algorithm have the same expression capabilities. The source is switched at random intervals, which means that the algorithm’s behavior can only be identified when it deviates from what is regarded as appropriate. The SWOZ approach is especially suitable for the controlled evaluation of synthesis algorithms that consider a limited set of behaviors. We evaluate a backchannel synthesis algorithm for speaker–listener dialogs using an asymmetric version of the framework. Human speakers talk to virtual listeners, that are either controlled by human listeners or by an algorithm. Speakers indicate when they feel they are no longer talking to a human listener. Analysis of these responses reveals patterns of inappropriate behavior in terms of quantity and timing of backchannels. These insights can be used to improve synthesis algorithms.

AB - The Switching Wizard of Oz (SWOZ) is a setup to evaluate human behavior synthesis algorithms in online face-to-face interactions. Conversational partners are represented to each other as virtual agents, whose animated behavior is either based on a synthesis algorithm, or driven by the actual behavior of the conversational partner. Human and algorithm have the same expression capabilities. The source is switched at random intervals, which means that the algorithm’s behavior can only be identified when it deviates from what is regarded as appropriate. The SWOZ approach is especially suitable for the controlled evaluation of synthesis algorithms that consider a limited set of behaviors. We evaluate a backchannel synthesis algorithm for speaker–listener dialogs using an asymmetric version of the framework. Human speakers talk to virtual listeners, that are either controlled by human listeners or by an algorithm. Speakers indicate when they feel they are no longer talking to a human listener. Analysis of these responses reveals patterns of inappropriate behavior in terms of quantity and timing of backchannels. These insights can be used to improve synthesis algorithms.

KW - EWI-24794

KW - HMI-IA: Intelligent Agents

KW - User study

KW - Perception

KW - IR-91465

KW - Listening Behavior

KW - Wizard of Oz

KW - METIS-305901

KW - Backchannels

U2 - 10.1007/s12193-013-0131-2

DO - 10.1007/s12193-013-0131-2

M3 - Article

VL - 8

SP - 109

EP - 117

JO - Journal on multimodal user interfaces

JF - Journal on multimodal user interfaces

SN - 1783-7677

IS - 1

ER -