Location

Salt Lake City, Utah

Date

23-6-2015

Session

Session 1 – Lectures Driver Behavior and Naturalistic Studies

Abstract

Hands-free voice interaction is an increasingly common option in new vehicles. Recent research suggests that hands-free interactions with speech-to-text systems may require significantly more cognitive effort than previously anticipated. This high level of mental workload may both keep drivers from using the technology and potentially create additional safety concerns for the driver. However, little prior research has measured the cognitive demands of simple voice based tasks using real-world systems. The current study evaluated the mental demands of a small set of auditory-vocal vehicle commands using five 2013 and one 2012 model year OEM infotainment systems. Results indicate that well executed voice systems impose little additional cognitive demand while poorly executed systems may significantly elevate workload.

Rights

Copyright © 2015 the author(s)

DC Citation

Proceedings of the Eighth International Driving Symposium on Human Factors in Driver Assessment, Training and Vehicle Design, June 22-25, 2015, Salt Lake City, Utah. Iowa City, IA: Public Policy Center, University of Iowa, 2015: 2-8.

Share

COinS
 
Jun 23rd, 12:00 AM

Mental Workload of Voice Interactions with 6 Real-World Driver Interfaces

Salt Lake City, Utah

Hands-free voice interaction is an increasingly common option in new vehicles. Recent research suggests that hands-free interactions with speech-to-text systems may require significantly more cognitive effort than previously anticipated. This high level of mental workload may both keep drivers from using the technology and potentially create additional safety concerns for the driver. However, little prior research has measured the cognitive demands of simple voice based tasks using real-world systems. The current study evaluated the mental demands of a small set of auditory-vocal vehicle commands using five 2013 and one 2012 model year OEM infotainment systems. Results indicate that well executed voice systems impose little additional cognitive demand while poorly executed systems may significantly elevate workload.