Battling Distracted Crossing

At Georgia Tech, one of the busiest places on campus is Technology Square. Even at nine in the morning, this area is bustling with people, all of whom are on different missions.There are people walking, driving, eating, studying, exercising, talking, and even listening to music. However, where the roads meet at 5th and Spring, all individuals, whether by car or by foot, come together to safely complete one common task: crossing the street. While widely overlooked, it is crucial to the proper functioning of the intersection.

As the name suggests, technology is important in the space. Certain safety features, such as the stoplights and the cross walk lights, rely on it to visually communicate information that facilitates the completion of the task. However, with the increasing dependency on cell phones and other devices that largely utilize visual technology, these safety features are beginning to become less effective. Fortunately, this can be combated through the addition of safety features that rely on vocal cues.

Pedestrians crossing the street at Tech Square. Source:www.glassdoor.com

For the distracted pedestrian or the disabled/blind, the addition of a voice interface would potentially prevent many accidents. Sensors would detect the presence of a person near the intersection, and the voice would alert the user if and when it is safe to cross. This would reduce not only the danger in the intersection but also the anxiety of both pedestrians and drivers. For drivers, a voice interface similar to that of a GPS would provide an additional safety measure when approaching an intersection. The system would utilize the driver’s position, information from the upcoming stop lights, and sensors near the crosswalk to alert the driver about changing lights and potential pedestrians. This information would be transmitted vocally through the radio, allowing the driver to concentrate on the road ahead.

When choosing a voice for both interfaces, similarity attraction is important. This is due to the fact that “people like voices that manifest personalities that are similar to their own”(Nass 41). At the intersection, the pedestrians and drivers have purpose and are determined to reach their destination; thus, it would make sense for the voice to be professional and straightforward, providing only the necessary information. It should have a male voice with a relatively high volume, a slightly deep pitch, medium pitch range, and an average speech rate. These characteristics would ensure that the voice comes across as knowledgeable and trustworthy but not intimidating. This is important because it would eliminate the possibility of the user feeling as if they are being told what to do; thus, a sense of equality between the user and the interface would be established through the voice, which is similar to that of the stereotypical copilot mentioned in Wired For Speech. However, it does differ in that the slower speech rate and higher volume would ensure clear understanding of the instructions given, which is crucial in a chaotic intersection.

In the future, the integration of a voice interface that connects drivers to pedestrians and provides the user with a comfortable experience would increase the safety and efficiency of the intersection at Tech Square.

One comment

  • Michael Bick

    Your idea to create an interface that will help both drivers and pedestrians cross the intersection safely is novel, but I disagree that a speech directed interface is optimal in this situation. As you pointed out, it is vital to consider similarity attraction when designing a speech directed interface. However, the intersection users come from a wide variety of backgrounds, have different emotions, and may not even speak the same language. Thus I believe your interface would benefit from a more universal signal than speech, such as loud, clear warning sounds.

Leave a Reply