New research conducted in the USA reveals that voice recognition systems designed to minimise driver distraction are actually likely to heighten driver distraction.
The research, carried out by the American Automobile Association's (AAA) Foundation for Traffic Safety, follows an initial phase conduced in 2013 that found many systems are complex, often inaccurate and not easy to operate. Using a variety of measuring tools to ascertain the degree of distraction caused by various voice-control systems, the research found cognitive distraction was not uncommon.
According to Bob Darbelnet, chief executive officer of AAA, the inadequacies of some systems could lead to drivers missing stop signs, pedestrians and other cars through the diversion of their attention focus from the road.
"We now understand that current shortcomings in these products, intended as safety features, may unintentionally cause greater levels of cognitive distraction," he said.
The AAA research suggested developers can improve the safety of their products through greater attention to usability during the design phase – a potential made clear in the disparity in distraction levels between various systems.
The research graded distraction into five basic levels: Listening to the radio rated as a category one distraction; talking on a hand-held or hands-free mobile phone resulted in a category two distraction; and using an error-free speech-to-text system to listen to and compose emails or texts was a category three distraction.
The major offender in the study was Chevy's My Link system which was found to bring high (level three) distraction, while Toyota's Entune system scored points as the least-distracting (level one) system of those listed.
The Mercedes-Benz COMAND system hovered between level three and level two, as did Ford's MyFord Touch, while Chrysler's Uconnect and Hyundai's Blue Link rated in level two.
Apple's Siri did less well again: In a separate assessment, the AAA found using Siri technology in hands and eyes-free mode generated a relatively higher, level four grade of distraction.
"It is clear that not all voice systems are created equal, and today's imperfect systems can lead to driver distraction," Mr. Darbelnet said.
The AAA is calling for developers to address key contributing factors to mental distraction including complexity, accuracy and time on task with the goal of making systems that are no more demanding than listening to the radio or an audiobook. AAA also plans to use its findings to continue a dialogue with policy makers, safety advocates and manufacturers.
Generally, the results of the research showed:
>> The accuracy of voice recognition software significantly influences the rate of distraction. Systems with low accuracy and reliability generated a high level (category three) of distraction.
>> Composing text messages and emails using in-vehicle technologies (category three) was more distracting than using these systems to listen to messages (category two).
>> The quality of the systems' voice had no impact on distraction levels – listening to a natural or synthetic voice both rated as a category two level of distraction.
According to the AAA, the good news for consumers is that the research shows it is possible to design hands-free technologies that are "less cognitively distracting".
And that includes you, Siri.