Talking to...uh...um...Machines: The Impact of Disfluent Speech Agents on Partner Models and Perspective Taking

TL;DR

This study investigates how speech disfluencies in dialogue agents influence human perceptions, partner models, and language behavior, revealing that disfluencies can enhance perceived competence and affect communication strategies.

Contribution

It provides novel insights into the effects of disfluencies in human-machine dialogue, highlighting their influence on partner perceptions and egocentric language production.

Findings

Disfluent agents are perceived as more competent.

Disfluencies increase egocentric communication behaviors.

No significant difference in perceived flexibility or human-likeness.

Abstract

Speech disfluencies play a role in perspective-taking and audience design in human-human communication (HHC), but little is known about their impact in human-machine dialogue (HMD). In an online Namer-Matcher task, sixty-one participants interacted with a speech agent using either fluent or disfluent speech. Participants completed a partner-modelling questionnaire (PMQ) both before and after the task. Post-interaction evaluations indicated that participants perceived the disfluent agent as more competent, despite no significant differences in pre-task ratings. However, no notable differences were observed in assessments of conversational flexibility or human-likeness. Our findings also reveal evidence of egocentric and allocentric language production when participants interact with speech agents. Interaction with disfluent speech agents appears to increase egocentric communication in comparison to fluent agents. Although the wide credibility intervals mean this effect is not clear-cut. We discuss potential interpretations of this finding, focusing on how disfluencies may impact partner models and language production in HMD.