A clip on camera you can take with you while jogging or in a museum, and it talks to you? It would be pretty embarrassing to be seen with it. This would work out better in professional settings, such as in a hospital, providing help to doctors.
It would sound like an American tourist by doing that.
(There’s lots of articles from US expats in europe, or european expats in the EU, showing how US-Americans tend to speak a lot louder than Europeans in quiet settings, from museums to restaurants)
This leads to an interesting question: Which culture should a voice assistant follow? Should there be multiple variants of each assistant?
That starts with phrases, but also applies to other concepts – different cultures have different orientation systems even (some use cardinal directions (north, east, south, west), some use relative directions (front, right, back, left), etc)
I never read the research about this but examples are http://anthroweb.ucsd.edu/~jhaviland/Publications/ETHOSw.Dia... and http://pubman.mpdl.mpg.de/pubman/item/escidoc:66622:3/compon... (very interesting stuff!).
Edit: I would highly recommend reading the 2nd paper (which includes some practical experiments testing how Guugu Yithimirr speakers thought about and remembered spatial positions and orientations). It's astonishing.
Even colors depend on cultures heavily. The ancient greek are believed not to have seperated between yellow and green, other cultures similar.
Internationalization is a lot harder than it seems to most people. And then there’s also accessibility.
Even with traditional UIs where everything is hand made it’s already an extremely huge task, but a conversational UI is far more personal.
It has to deal with things like how much privacy or directness is expected in cultures, with taboos, it has to have a full perceptional model of the person who will hear it to be able to properly handle all this.
(Maybe.)
That's what museum tour guides, human or automated, do today.