EVALUATION OF ECA GESTURE STRATEGIES FOR ROBUST HUMAN-MACHINE INTERACTION

Autor: María del Carmen Rodríguez Gancedo, Beatriz López Mencía, José Relaño Gil, Luis A. Hernández Gómez, David Díaz Pardo de Vera, Álvaro Hernández Trapote
Rok vydání: 2008
Předmět:
Zdroj: The International Journal Of Semantic Computing, ISSN 1793-351X, 2008-03, Vol. 2, No. 1
Archivo Digital UPM
Universidad Politécnica de Madrid
ISSN: 1793-7108
1793-351X
DOI: 10.1142/s1793351x08000373
Popis: Embodied Conversational Agents (ECAs) offer us the possibility to design pleasant and efficient human-machine interaction. In this paper we present an evaluation scheme to compare dialogue-based speaker authentication and information retrieval systems with and without ECAs on the interface. We used gestures and other visual cues to improve fluency and robustness of interaction with these systems. Our tests results suggest that when an ECA is present users perceive fewer system errors, their frustration levels are lower, turn-changing goes more smoothly, the interaction experience is more enjoyable, and system capabilities are generally perceived more positively than when no ECA is present. However, the ECA seems to intensify the users' privacy concerns.
Databáze: OpenAIRE