"Xbox volume down." "cancel. select. xbox select. xbox. xbox. select. cancel. volume down. no. fuck you you piece of shit x box volume down. THANK YOU."
Alternatively, it could be some kind of sound that's not common to English. In fact, your could make up a whole command structure based on sound "gestures". It would sound funny, but the ease of use would trump those awkward verbal commands. The sounds could mimic natural sounds for mnemonic ease.
It could be made to sound _hilarious_! :-)
Or I'm just preparing to be one of the "good ones" after the inevitable robot revolution.
I FOR ONE WELCOME OUR NEW ROBOT OVERLORDS
Subject change: it'd be nice if these things provided feedback like how much noise it hears, how clearly it thinks I'm speaking, how well it thinks it understood, etc. This would go a long way to helping those moments when I'm being impatient because it's just not understanding.
Classic ID-10-T error.
I think we'll see more of this as more customer service robots make their way into retail space.