Paper Number

ICIS2025-2629

Paper Type

Complete

Abstract

This study explores how AI instructor voice characteristics, gender (male vs. female), and style (humanoid vs. robotic) influence learning in simulated driving. Drawing on dual-coding theory, it is hypothesized that voice-gender and audio fidelity shape cognitive effort and emotional responses, thus impacting immediate driving reactions and later performance. A laboratory experiment using a driving simulator was conducted to test the hypotheses. The findings revealed that male voices and humanoid voices generally improve driving performance. Specifically, male humanoid voices enable faster responses and better learning retention. Robotic voices prompted faster immediate reactions, but hindered later performance. Cognitive effort mediated the positive impact of male voices on learning, whereas confused emotions mediated the negative impact of robotic voices on immediate responses. This study extends AI-HCI research by demonstrating how AI as an instructor, rather than an assistant, can shape learning through voice design.

Comments

06-SocialGood

Download

Share

COinS
 
Dec 14th, 12:00 AM

Talk, Drive, React: How AI Voice Gender and Style Shape Learning in Simulated Driving

This study explores how AI instructor voice characteristics, gender (male vs. female), and style (humanoid vs. robotic) influence learning in simulated driving. Drawing on dual-coding theory, it is hypothesized that voice-gender and audio fidelity shape cognitive effort and emotional responses, thus impacting immediate driving reactions and later performance. A laboratory experiment using a driving simulator was conducted to test the hypotheses. The findings revealed that male voices and humanoid voices generally improve driving performance. Specifically, male humanoid voices enable faster responses and better learning retention. Robotic voices prompted faster immediate reactions, but hindered later performance. Cognitive effort mediated the positive impact of male voices on learning, whereas confused emotions mediated the negative impact of robotic voices on immediate responses. This study extends AI-HCI research by demonstrating how AI as an instructor, rather than an assistant, can shape learning through voice design.

When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.