In my next research project, in short, I am going to be writing a program in
which my program will be accepting spoken answers from subjects (which are
mildly retarded).

My program will show 4 pictures at one time, a different picture in each of
the four different quadrants of the monitor.  The pictures might be a dog,
cow, cat, and a mule.

The subject will say either dog, cat, cow, or mule.  I need my program to
capture which animal was spoken by the subject.  Then based on the subjects
response my program will decide if the answer given is correct or incorrect
and do whatever else.

So my question is:

Can I or do I use FutureBasic to do everything?

Or do I need to use a combination of FutureBasic and something like Voice
Power Pro, Via Voice from IBM, or something from Dragon Systems to get the
job done?

Or is this even possible?  If so, have any of you ever worked on a such a
project?

I am currently using FB II.

Thanks for any assistance!
Doug Hull