It uses the vibrations from the wearer's jaw to determine who is speaking. The geniuses behind an advanced piece of future tech didn't make so basic a mistake every child on the internet could joke about it in seconds.
...I mean, Microsoft did make that exact mistake with their Xbox One livestream giving commands the Xbox 360's people were watching it on, but IN THIS CASE that didn't happen.
So, what you're saying is that I need to mix that into a music track with a lot of bass and repetition that can be blasted from cars and other sources of phat audio.