John Wojnaroski wrote:
----- Original Message -----
From: "Boris Koenig" <[EMAIL PROTECTED]>

What type of project is that ? - (FlightGear related ?)

See the FG Project webpage for details

oh well, it's always the obvious ... :-)

3) One of the advantages of TTS (at least as I see it) is you don't have to
create snippets or prestore anything.

Sure, right - I was only referring to these (downloadable) "snippets" as a supplement for the whole thing itself, particularly for those users who won't set up a TTS, be it because they don't want to or it's simply not that easy, so for such cases it would be possible to use a centralized TTS that delivers the snippets on demand - of course that'd be pointless when you got a TTS running locally.

One has the luxury of total and complete freedom to create any and all
> possible combinations of words within
the established language model and create the audio in real time.

4) Speech recognition for converting audio to text is just about perfect.

Well - you may be right, also getting the recognition rate sufficiently
high is certainly less an issue for native speakers - except maybe Australians ;-) but for average foreigner it's quite an adventure
to make a speech recognition engine recognize his/her English ;-)

The trick, as you noted,  is having the machine "understand" what was

I'm going to think more about that later, but probably there are others, too who have ideas about how to realize the logics or troubleshoot certain problems for such a thing as a fully interactive scriptable ATC<->TTS engine - so, maybe we can even come up with a draft for a -hopefully- working logical implementation of this whole thing.

--------- Boris

Flightgear-devel mailing list

Reply via email to