A meta-analysis of in-vehicle and nomadic voice-recognition system interaction and driving performance. (September 2017)

• Record Type: Journal Article
• Authors: Simmons, Sarah M.; Caird, Jeff K.; Steel, Piers
• Is Part Of: Accident analysis and prevention. Volume 106(2017)
• Page Start: 31
• Page End: 43
• Publication Date: 2017-09
• Subjects: Driver distraction -- Driving performance -- Voice-recognition -- Speech-to-text -- Meta-analysis; Accidents -- Prevention -- Periodicals; Accident Prevention -- Periodicals; Accidents -- Prévention -- Périodiques; 363.106
• DOI: 10.1016/j.aap.2017.05.013
• Languages: English
• ISSNs: 0001-4575

Abstract

Highlights: Meta-analysis of voice-recognition system interaction on driving performance. Voice-recognition system interaction while driving has a distraction cost. Some improved performance relative to visual-manual systems. Abstract: Driver distraction is a growing and pervasive issue that requires multiple solutions. Voice-recognition (V-R) systems may decrease the visual-manual (V-M) demands of a wide range of in-vehicle system and smartphone interactions. However, the degree that V-R systems integrated into vehicles or available in mobile phone applications affect driver distraction is incompletely understood. A comprehensive meta-analysis of experimental studies was conducted to address this knowledge gap. To meet study inclusion criteria, drivers had to interact with a V-R system while driving and doing everyday V-R tasks such as dialing, initiating a call, texting, emailing, destination entry or music selection. Coded dependent variables included detection, reaction time, lateral position, speed and headway. Comparisons of V-R systems with baseline driving and/or a V-M condition were also coded. Of 817 identified citations, 43 studies involving 2000 drivers and 183 effect sizes ( r ) were analyzed in the meta-analysis. Compared to baseline, driving while interacting with a V-R system is associated with increases in reaction time and lane positioning, and decreases in detection. When V-M systems were compared to V-R systems, drivers had slightly better performance with the latter system on reaction time, lane positioning and headway. Although V-R systems have some driving performance advantages over V-M systems, they have a distraction cost relative to driving without any system at all. The pattern of results indicates that V-R systems impose moderate distraction costs on driving. In addition, drivers minimally engage in compensatory performance adjustments such as reducing speed and increasing headway while using V-R systems. Implications of the results for theory, design guidelines and future research are discussed.