Perceptual evaluation of backchannel strategies for artificial listeners

Research output: Contribution to journalArticleAcademicpeer-review

7 Citations (Scopus)

Abstract

Artificial listeners are virtual agents that can listen attentively to a human speaker in a dialog. In this paper, we present two experiments where we investigate the perception of rule-based backchannel strategies for artificial listeners. In both, we collect subjective judgements of humans who observe a video of a speaker together with a corresponding animation of an artificial listener. In the first experiment, we evaluate six rule-based strategies that differ in the types of features (e.g. prosody, gaze) they consider. The ratings are given at the level of a speech turn and can be considered a measure for how human-like the generated listening behavior is perceived. In the second experiment, we systematically investigate the effect of the quantity, type and timing of backchannels within the discourse of the speaker. Additionally, we asked human observers to press a button whenever they thought a generated backchannel occurrence was inappropriate. Both experiments together give insights in the factors, both from an observation and generation point-of-view, that influence the perception of backchannel strategies for artificial listeners.
Original languageUndefined
Pages (from-to)235-253
Number of pages19
JournalAutonomous agents and multi-agent systems
Volume27
Issue number2
DOIs
Publication statusPublished - Sep 2013

Keywords

  • EC Grant Agreement nr.: FP7/231287
  • EC Grant Agreement nr.: FP7/211486
  • EWI-23302
  • HMI-IA: Intelligent Agents
  • IR-86110
  • perception study
  • Backchannel
  • Artificial Listener
  • METIS-297621
  • Listening Behavior

Cite this

@article{5bbef4baca2446de9c8161327e08aaf3,
title = "Perceptual evaluation of backchannel strategies for artificial listeners",
abstract = "Artificial listeners are virtual agents that can listen attentively to a human speaker in a dialog. In this paper, we present two experiments where we investigate the perception of rule-based backchannel strategies for artificial listeners. In both, we collect subjective judgements of humans who observe a video of a speaker together with a corresponding animation of an artificial listener. In the first experiment, we evaluate six rule-based strategies that differ in the types of features (e.g. prosody, gaze) they consider. The ratings are given at the level of a speech turn and can be considered a measure for how human-like the generated listening behavior is perceived. In the second experiment, we systematically investigate the effect of the quantity, type and timing of backchannels within the discourse of the speaker. Additionally, we asked human observers to press a button whenever they thought a generated backchannel occurrence was inappropriate. Both experiments together give insights in the factors, both from an observation and generation point-of-view, that influence the perception of backchannel strategies for artificial listeners.",
keywords = "EC Grant Agreement nr.: FP7/231287, EC Grant Agreement nr.: FP7/211486, EWI-23302, HMI-IA: Intelligent Agents, IR-86110, perception study, Backchannel, Artificial Listener, METIS-297621, Listening Behavior",
author = "Poppe, {Ronald Walter} and Truong, {Khiet Phuong} and Heylen, {Dirk K.J.}",
note = "eemcs-eprint-23302",
year = "2013",
month = "9",
doi = "10.1007/s10458-013-9219-z",
language = "Undefined",
volume = "27",
pages = "235--253",
journal = "Autonomous agents and multi-agent systems",
issn = "1387-2532",
publisher = "Springer",
number = "2",

}

Perceptual evaluation of backchannel strategies for artificial listeners. / Poppe, Ronald Walter; Truong, Khiet Phuong; Heylen, Dirk K.J.

In: Autonomous agents and multi-agent systems, Vol. 27, No. 2, 09.2013, p. 235-253.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Perceptual evaluation of backchannel strategies for artificial listeners

AU - Poppe, Ronald Walter

AU - Truong, Khiet Phuong

AU - Heylen, Dirk K.J.

N1 - eemcs-eprint-23302

PY - 2013/9

Y1 - 2013/9

N2 - Artificial listeners are virtual agents that can listen attentively to a human speaker in a dialog. In this paper, we present two experiments where we investigate the perception of rule-based backchannel strategies for artificial listeners. In both, we collect subjective judgements of humans who observe a video of a speaker together with a corresponding animation of an artificial listener. In the first experiment, we evaluate six rule-based strategies that differ in the types of features (e.g. prosody, gaze) they consider. The ratings are given at the level of a speech turn and can be considered a measure for how human-like the generated listening behavior is perceived. In the second experiment, we systematically investigate the effect of the quantity, type and timing of backchannels within the discourse of the speaker. Additionally, we asked human observers to press a button whenever they thought a generated backchannel occurrence was inappropriate. Both experiments together give insights in the factors, both from an observation and generation point-of-view, that influence the perception of backchannel strategies for artificial listeners.

AB - Artificial listeners are virtual agents that can listen attentively to a human speaker in a dialog. In this paper, we present two experiments where we investigate the perception of rule-based backchannel strategies for artificial listeners. In both, we collect subjective judgements of humans who observe a video of a speaker together with a corresponding animation of an artificial listener. In the first experiment, we evaluate six rule-based strategies that differ in the types of features (e.g. prosody, gaze) they consider. The ratings are given at the level of a speech turn and can be considered a measure for how human-like the generated listening behavior is perceived. In the second experiment, we systematically investigate the effect of the quantity, type and timing of backchannels within the discourse of the speaker. Additionally, we asked human observers to press a button whenever they thought a generated backchannel occurrence was inappropriate. Both experiments together give insights in the factors, both from an observation and generation point-of-view, that influence the perception of backchannel strategies for artificial listeners.

KW - EC Grant Agreement nr.: FP7/231287

KW - EC Grant Agreement nr.: FP7/211486

KW - EWI-23302

KW - HMI-IA: Intelligent Agents

KW - IR-86110

KW - perception study

KW - Backchannel

KW - Artificial Listener

KW - METIS-297621

KW - Listening Behavior

U2 - 10.1007/s10458-013-9219-z

DO - 10.1007/s10458-013-9219-z

M3 - Article

VL - 27

SP - 235

EP - 253

JO - Autonomous agents and multi-agent systems

JF - Autonomous agents and multi-agent systems

SN - 1387-2532

IS - 2

ER -