Backchannel Strategies for Artificial Listeners

Ronald Walter Poppe; Khiet Phuong Truong; Dennis Reidsma; Dirk K.J. Heylen

doi:10.1007/978-3-642-15892-6_16

Backchannel Strategies for Artificial Listeners

Ronald Walter Poppe, Khiet Phuong Truong, Dennis Reidsma, Dirk K.J. Heylen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

44 Citations (Scopus)

323 Downloads (Pure)

Abstract

We evaluate multimodal rule-based strategies for backchannel (BC) generation in face-to-face conversations. Such strategies can be used by artificial listeners to determine when to produce a BC in dialogs with human speakers. In this research, we consider features from the speaker’s speech and gaze. We used six rule-based strategies to determine the placement of BCs. The BCs were performed by an intelligent virtual agent using nods and vocalizations. In a user perception experiment, participants were shown video fragments of a human speaker together with an artificial listener who produced BC behavior according to one of the strategies. Participants were asked to rate how likely they thought the BC behavior had been performed by a human listener. We found that the number, timing and type of BC had a significant effect on how human-like the BC behavior was perceived.

Original language	Undefined
Title of host publication	International Conference on Intelligent Virtual Agents (IVA)
Editors	Jan Allbeck, Norman Badler, Timothy Bickmore, Catherine Pelachaud, Alla Safonova
Place of Publication	Berlin
Publisher	Springer
Pages	146-158
Number of pages	13
ISBN (Print)	978-3-642-15891-9
DOIs	https://doi.org/10.1007/978-3-642-15892-6_16
Publication status	Published - Sept 2010
Event	10th International Conference on Intelligent Virtual Agents, IVA 2010 - Philadelphia, United States Duration: 20 Sept 2010 → 22 Sept 2010 Conference number: 10

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer Verlag
Volume	6356

Conference

Conference	10th International Conference on Intelligent Virtual Agents, IVA 2010
Abbreviated title	IVA
Country/Territory	United States
City	Philadelphia
Period	20/09/10 → 22/09/10

Keywords

IR-73095
METIS-271024
Artificial Listener
Backchannel
HMI-IA: Intelligent Agents
Perception
Nod
EWI-18440
EC Grant Agreement nr.: FP7/211486
Continuer

Access to Document

10.1007/978-3-642-15892-6_16

fulltext

Cite this

Poppe, R. W., Truong, K. P., Reidsma, D., & Heylen, D. K. J. (2010). Backchannel Strategies for Artificial Listeners. In J. Allbeck, N. Badler, T. Bickmore, C. Pelachaud, & A. Safonova (Eds.), International Conference on Intelligent Virtual Agents (IVA) (pp. 146-158). (Lecture Notes in Computer Science; Vol. 6356). Springer. https://doi.org/10.1007/978-3-642-15892-6_16

@inproceedings{2d98b60cd35343f9b760f5a04a7b360d,

title = "Backchannel Strategies for Artificial Listeners",

abstract = "We evaluate multimodal rule-based strategies for backchannel (BC) generation in face-to-face conversations. Such strategies can be used by artificial listeners to determine when to produce a BC in dialogs with human speakers. In this research, we consider features from the speaker{\textquoteright}s speech and gaze. We used six rule-based strategies to determine the placement of BCs. The BCs were performed by an intelligent virtual agent using nods and vocalizations. In a user perception experiment, participants were shown video fragments of a human speaker together with an artificial listener who produced BC behavior according to one of the strategies. Participants were asked to rate how likely they thought the BC behavior had been performed by a human listener. We found that the number, timing and type of BC had a significant effect on how human-like the BC behavior was perceived.",

keywords = "IR-73095, METIS-271024, Artificial Listener, Backchannel, HMI-IA: Intelligent Agents, Perception, Nod, EWI-18440, EC Grant Agreement nr.: FP7/211486, Continuer",

author = "Poppe, {Ronald Walter} and Truong, {Khiet Phuong} and Dennis Reidsma and Heylen, {Dirk K.J.}",

note = "10.1007/978-3-642-15892-6_16 ; 10th International Conference on Intelligent Virtual Agents, IVA 2010 ; Conference date: 20-09-2010 Through 22-09-2010",

year = "2010",

month = sep,

doi = "10.1007/978-3-642-15892-6_16",

language = "Undefined",

isbn = "978-3-642-15891-9",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "146--158",

editor = "Jan Allbeck and Norman Badler and Timothy Bickmore and Catherine Pelachaud and Alla Safonova",

booktitle = "International Conference on Intelligent Virtual Agents (IVA)",

address = "Germany",

}

Poppe, RW, Truong, KP , Reidsma, D & Heylen, DKJ 2010, Backchannel Strategies for Artificial Listeners. in J Allbeck, N Badler, T Bickmore, C Pelachaud & A Safonova (eds), International Conference on Intelligent Virtual Agents (IVA). Lecture Notes in Computer Science, vol. 6356, Springer, Berlin, pp. 146-158, 10th International Conference on Intelligent Virtual Agents, IVA 2010, Philadelphia, Pennsylvania, United States, 20/09/10. https://doi.org/10.1007/978-3-642-15892-6_16

Backchannel Strategies for Artificial Listeners. / Poppe, Ronald Walter; Truong, Khiet Phuong ; Reidsma, Dennis et al.
International Conference on Intelligent Virtual Agents (IVA). ed. / Jan Allbeck; Norman Badler; Timothy Bickmore; Catherine Pelachaud; Alla Safonova. Berlin: Springer, 2010. p. 146-158 (Lecture Notes in Computer Science; Vol. 6356).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Backchannel Strategies for Artificial Listeners

AU - Poppe, Ronald Walter

AU - Truong, Khiet Phuong

AU - Reidsma, Dennis

AU - Heylen, Dirk K.J.

N1 - Conference code: 10

PY - 2010/9

Y1 - 2010/9

N2 - We evaluate multimodal rule-based strategies for backchannel (BC) generation in face-to-face conversations. Such strategies can be used by artificial listeners to determine when to produce a BC in dialogs with human speakers. In this research, we consider features from the speaker’s speech and gaze. We used six rule-based strategies to determine the placement of BCs. The BCs were performed by an intelligent virtual agent using nods and vocalizations. In a user perception experiment, participants were shown video fragments of a human speaker together with an artificial listener who produced BC behavior according to one of the strategies. Participants were asked to rate how likely they thought the BC behavior had been performed by a human listener. We found that the number, timing and type of BC had a significant effect on how human-like the BC behavior was perceived.

AB - We evaluate multimodal rule-based strategies for backchannel (BC) generation in face-to-face conversations. Such strategies can be used by artificial listeners to determine when to produce a BC in dialogs with human speakers. In this research, we consider features from the speaker’s speech and gaze. We used six rule-based strategies to determine the placement of BCs. The BCs were performed by an intelligent virtual agent using nods and vocalizations. In a user perception experiment, participants were shown video fragments of a human speaker together with an artificial listener who produced BC behavior according to one of the strategies. Participants were asked to rate how likely they thought the BC behavior had been performed by a human listener. We found that the number, timing and type of BC had a significant effect on how human-like the BC behavior was perceived.

KW - IR-73095

KW - METIS-271024

KW - Artificial Listener

KW - Backchannel

KW - HMI-IA: Intelligent Agents

KW - Perception

KW - Nod

KW - EWI-18440

KW - EC Grant Agreement nr.: FP7/211486

KW - Continuer

U2 - 10.1007/978-3-642-15892-6_16

DO - 10.1007/978-3-642-15892-6_16

M3 - Conference contribution

SN - 978-3-642-15891-9

T3 - Lecture Notes in Computer Science

SP - 146

EP - 158

BT - International Conference on Intelligent Virtual Agents (IVA)

A2 - Allbeck, Jan

A2 - Badler, Norman

A2 - Bickmore, Timothy

A2 - Pelachaud, Catherine

A2 - Safonova, Alla

PB - Springer

CY - Berlin

T2 - 10th International Conference on Intelligent Virtual Agents, IVA 2010

Y2 - 20 September 2010 through 22 September 2010

ER -