|
Post by morsealworth on Apr 7, 2016 9:56:48 GMT
Now that I think about it, wit would be actually easier to implement voice control than motion gestures if we're talking about VR. People all have different body proportions and therefore different scopes of gestures, but voice recognition is pretty much the same.
And there are already enough foundations to build on.The question is: What OS are present in the scope of the game?
|
|
|
Post by echocdelta on Apr 8, 2016 2:48:41 GMT
Voice recognition is actually really difficult due to people talking in different accents or tones. Also localisation goes right out the window - every language requires a new set of commands, new set of tones, accents etc.
|
|
|
Post by morsealworth on Apr 8, 2016 6:57:47 GMT
That's why I'm talking about OS in the scope. Windows has its own voice recognition engine with its own API. That's why Thu'uMic and In Verbis Virtus work without a hitch despite both having little to no budget.
Don't really know about other OS, though.
|
|
Griffork
Genesis staff
Posts: 10
I like: Enthusiasm, VR, VFX, shiny & pretty things, Caustics (don't get me started), Making shiny & pretty things, other people's art, 90fps.
I don't like: anything I make that doesn't meet my seal of approval.
|
Post by Griffork on Apr 26, 2016 0:02:37 GMT
That's why I'm talking about OS in the scope. Windows has its own voice recognition engine with its own API. That's why Thu'uMic and In Verbis Virtus work without a hitch despite both having little to no budget. Don't really know about other OS, though. Linux most certainly doesn't. It doesn't always contain text to speech services let alone speech to text (I found that out the hard way).
|
|
|
Post by morsealworth on Apr 26, 2016 8:14:38 GMT
Oh, if you have Linux in your scope. My apologies, I'm not helpful.
|
|