Non-humanlike spoken dialogue: a design perspective

Authors:
Kotaro Funakoshi;Mikio Nakano;Kazuki Kobayashi;Takanori Komatsu;Seiji Yamada
Affiliations:
Honda Research Institute Japan Co., Ltd., Honcho, Wako, Saitama, Japan;Honda Research Institute Japan Co., Ltd., Honcho, Wako, Saitama, Japan;Shinshu University, Wakasato, Nagano, Nagano, Japan;Shinshu University, Tokida, Ueda, Nagano, Japan;National Institute of Informatics, Hitotsubashi, Chiyoda, Tokyo, Japan
Venue:
SIGDIAL '10 Proceedings of the 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Year:
2010

Citing 3
Cited 4

How quickly should communication robots respond?

Proceedings of the 3rd ACM/IEEE international conference on Human robot interaction
A finite-state turn-taking model for spoken dialog systems

NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Artificial subtle expressions: intuitive notification methodology of artifacts

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems

Effects of different types of artifacts on interpretations of artificial subtle expressions (ASEs)

CHI '11 Extended Abstracts on Human Factors in Computing Systems
Interpretations of artificial subtle expressions (ASEs) in terms of different types of artifact: a comparison of an on-screen artifact with a robot

ACII'11 Proceedings of the 4th international conference on Affective computing and intelligent interaction - Volume Part II
Can users live with overconfident or unconfident systems?: a comparison of artificial subtle expressions with human-like expression

CHI '12 Extended Abstracts on Human Factors in Computing Systems
Expressing a robot's confidence with motion-based artificial subtle expressions

CHI '13 Extended Abstracts on Human Factors in Computing Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a non-humanlike spoken dialogue design, which consists of two elements: non-humanlike turn-taking and non-humanlike acknowledgment. Two experimental studies are reported in this paper. The first study shows that the proposed non-humanlike spoken dialogue design is effective for reducing speech collisions. It also presents pieces of evidence that show quick humanlike turn-taking is less important in spoken dialogue system design. The second study supports a hypothesis found in the first study that user preference on response timing varies depending on interaction patterns. Upon receiving these results, this paper suggests a practical design guideline for spoken dialogue systems.