The Effects of an Embodied Pedagogical Agent’s Synthetic Speech Accent on Learning Outcomes
Abstract
Modern text-to-speech engines can be an effective speech choice for embodied virtual pedagogical agents. However, it is not known how synthesized accents influence learning outcomes and perceptions of the agent. In this paper, we conducted a between-subjects experiment (n=60) to determine the effect of a pedagogical agent’s machine synthesized text-to-speech accent (United States English or Indian English) on learning outcomes and perceptions of the agent for students in the United States. Our results indicate that learner gender interacts with synthesized speech accent to significantly affect learning outcomes and perceptions of the agent. Our results reveal that a foreign synthetic speech accent may affect the learning outcomes of female university students (n=30), but not male university students (n=30). Finally, our results indicate that learner gender interacts with synthesized speech accent to affect perceptions of the pedagogical agent’s human-likeness. We provide novel insights on the differences between male and female learners for interactions with pedagogical agents with synthetic TTS accents.
