Additional Findings on the Multi-Modal Demands of “Voice-Command” Interfaces 2016-01-1428

This paper presents the results of a study of how people interacted with a production voice-command based interface while driving on public roadways. Tasks included phone contact calling, full address destination entry, and point-of-interest (POI) selection. Baseline driving and driving while engaging in multiple-levels of an auditory-vocal cognitive reference task and manual radio tuning were used as comparison points. Measures included self-reported workload, task performance, physiological arousal, glance behavior, and vehicle control for an analysis sample of 48 participants (gender balanced across ages 21-68). Task analysis and glance measures confirm earlier findings that voice-command interfaces do not always allow the driver to keep their hands on the wheel and eyes on the road, as some assume. Self-reported workload, task completion time, glance metrics, and error rates varied significantly across the tasks, highlighting the importance of evaluating a particular design characteristic for specific tasks and exercising caution in generalizing across this class of user interfaces. For example, the “one-shot” voice-command structure in the study vehicle was associated with very low workload and error rates for phone contact calling, but much higher values for destination address entry and POI selection. Total task and eyes-off-road time were also relatively high for the latter tasks. However, mean single glance duration was nominally lower and the impact on major steering wheel reversals was less during the voice command tasks than during manual radio tuning, suggesting the importance of considering the comprehensive demand of an interface relative to other tasks in which the driver might engage.