An architecture for fluid real-time conversational agents: Integrating incremental output generation and input processing

Kopp S, van Welbergen H, Yaghoubzadeh R, Buschmeier H (2014)
Journal on Multimodal User Interfaces 8: 97-108.

Zeitschriftenaufsatz | Veröffentlicht | Englisch
 
Download
OA
Abstract / Bemerkung
Embodied conversational agents still do not achieve the fluidity and smoothness of natural conversational interaction. One main reason is that current system often respond with big latencies and in inflexible ways. We argue that to overcome these problems, real-time conversational agents need to be based on an underlying architecture that provides two essential features for fast and fluent behavior adaptation: a close bi-directional coordination between input processing and output generation, and incrementality of processing at both stages. We propose an architectural framework for conversational agents [Artificial Social Agent Platform (ASAP)] providing these two ingredients for fluid real-time conversation. The overall architectural concept is described, along with specific means of specifying incremental behavior in BML and technical implementations of different modules. We show how phenomena of fluid real- time conversation, like adapting to user feedback or smooth turn-keeping, can be realized with ASAP and we describe in detail an example real-time interaction with the implemented system.
Stichworte
Fluid real-time interaction; Embodied conversational agents architecture; Incremental processing; Generation–interpretation coordination; BMLA; ASAP
Erscheinungsjahr
2014
Zeitschriftentitel
Journal on Multimodal User Interfaces
Band
8
Seite(n)
97-108
ISSN
1783-7677
eISSN
1783-8738
Page URI
https://pub.uni-bielefeld.de/record/2637332

Zitieren

Kopp S, van Welbergen H, Yaghoubzadeh R, Buschmeier H. An architecture for fluid real-time conversational agents: Integrating incremental output generation and input processing. Journal on Multimodal User Interfaces. 2014;8:97-108.
Kopp, S., van Welbergen, H., Yaghoubzadeh, R., & Buschmeier, H. (2014). An architecture for fluid real-time conversational agents: Integrating incremental output generation and input processing. Journal on Multimodal User Interfaces, 8, 97-108. doi:10.1007/s12193-013-0130-3
Kopp, S., van Welbergen, H., Yaghoubzadeh, R., and Buschmeier, H. (2014). An architecture for fluid real-time conversational agents: Integrating incremental output generation and input processing. Journal on Multimodal User Interfaces 8, 97-108.
Kopp, S., et al., 2014. An architecture for fluid real-time conversational agents: Integrating incremental output generation and input processing. Journal on Multimodal User Interfaces, 8, p 97-108.
S. Kopp, et al., “An architecture for fluid real-time conversational agents: Integrating incremental output generation and input processing”, Journal on Multimodal User Interfaces, vol. 8, 2014, pp. 97-108.
Kopp, S., van Welbergen, H., Yaghoubzadeh, R., Buschmeier, H.: An architecture for fluid real-time conversational agents: Integrating incremental output generation and input processing. Journal on Multimodal User Interfaces. 8, 97-108 (2014).
Kopp, Stefan, van Welbergen, Herwin, Yaghoubzadeh, Ramin, and Buschmeier, Hendrik. “An architecture for fluid real-time conversational agents: Integrating incremental output generation and input processing”. Journal on Multimodal User Interfaces 8 (2014): 97-108.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2019-09-06T09:18:19Z
MD5 Prüfsumme
512720b12048ccba6117c1ed3d36f8be