I have been posting info about my current project with emphasis on the SPEECH RECOGNITION aspects. Here is a posting I put out on YAHOO.
In my latest project utilizing several PIC microcontrollers, I need to have
communication between the system and the user – who may be a random
operator – say at an exhibit. Besides LCD’s and other types of displays, the
computer will communicate with a menu of voice messages using a
Chipcorder. But I want the operator to reply in a small vocabulary of spoken
words – IWR they call it – isolated word recognition.
Now I am beginning to learn there are a number of chips out there called
VPRs – voice recognition processors.
However, I want to try my hand at the nitty-gritty of speech recognition
circuitry myself. I am learning about A/Ds and DACs and I want to use a mike and an amp and digitize some individual words and see what the templates of the
sigs looks like. Then I would like to develop algorithms for comparing one
digitized template against another. Sound like fun to anyone?
Why let those engineers who developed these VRPs have all the fun? I like to
hear if anybody has tried one form or another of speech recognition.