Anyone knows something about that ? Would like to do something with it like making a program that responds when I say a word.
So anyone knows something ?
My guess would be it has something too do with the comparing of sound waves, but I honestly don't have a clue.
Yea, I ain't actualy a expert on sound, I can do some stuff in c++ and some sfml but it would be awesome if I could do a speech thingie.
There is the microsoft Speech API
[url]http://www.microsoft.com/speech/speech2007/default.mspx[/url]
I think the way it is done is that it has a sound file for each command, like start or play or whatever and all it does is compare the input too the sound files it has and chooses the right command by figuring out which sound file is the most fitting too the input.
Or recording it many different times from different persons to find characteristics and then trying to find those in the sound-input.
I agree with Zombuster, go with Microsoft's API. I've heard you can get basic recognition working in less than an hour with it easily.
[url]http://www.microsoft.com/speech/speech2007/default.mspx[/url]
Or you could have the option for the user to record the commands in his own voice, like on PDA's when you can write each letter like you would write it so it recognizes it more often.
Sorry, you need to Log In to post a reply to this thread.
