This is something I've been thinking is becoming more problematic as well as an opportunity for real ubiquity. I have 3 separate devices nearby that are Google Now voice activated (the newer devices support this even if the screen is off), and they will sometimes trigger at the same time accidentally.
Since the processing is cloud based, and they know my identity, why don't the devices recognize this fact and cooperate. Instead of just 7 beam forming mics in the Echo, if you have two within hearing distance you could have the benefit of 14 and a unified response. Don't tie the request & response to a particular device, instead think of it as ubiquitous network that moves with you as you walk around the household, you should be able to continue your conversation from one room to the next seamlessly.