Embodied conversational agents for voice-biometric interfaces

Abstract

In this article we present a research scheme which aims to analyze the use of Embodied Conversational Agent (ECA) technology to improve the robustness and acceptability of speaker enrolment and verification dialogues designed to provide secure access through natural and intuitive speaker recognition. In order to find out the possible effects of the visual information channel provided by the ECA, tests were carried out in which users were divided into two groups, each interacting with a different interface (metaphor): an ECA Metaphor group -with an ECA-, and a VOICE Metaphor group -without an ECA-. Our evaluation methodology is based on the ITU-T P.851 recommendation for spoken dialogue system evaluation, which we have complemented to cover particular aspects with regard to the two major extra elements we have incorporated: secure access and an ECA. Our results suggest that likeability-type factors and system capabilities are perceived more positively by the ECA metaphor users than by the VOICE metaphor users. However, the ECA's presence seems to intensify users' privacy concerns.

“Funny How?” A Serious Look at Humor in Conversational Agents

“…As these devices commonly tend to mimic human-like behavior and characteristics, they are often treated by users like a human counterpart [57], a common instance of anthropomorphism which has been thoroughly documented by researchers working within the Computers are Social Actors paradigm [45]. This phenomenon is partially caused due to the design of such devices, as human-likeness in human-computer interaction (HCI) has shown to be effective in increasing trust, loyalty, and engagement [7,24,29]. Incorporating human-like qualities into products has often been found to be advantageous [22] and has the potential to establish a sense of emotional attachment between the user and the product [72].…”