0

I want to make a program using Windows speech recognition and the respective .NET API and I was wondering, will the program automatically use the grammar and all the data that has been collected from the training of the recognition engine? Or will I have to force it? And if it has to be forced, how will that be ahcieved? The language to be used is C#.

Noob Doob
  • 1,757
  • 3
  • 19
  • 27
  • Have you tried SpeechRecognizer class http://msdn.microsoft.com/en-us/library/office/hh361683(v=office.14).aspx ? – Sergey Malyutin Oct 01 '14 at 11:41
  • You can also check my sample with SpeechRecognition engine used with Kinect as a audio source. Reuse it with another audio source should not be a problem. https://github.com/tkowalczyk/KinectAudioConsoleApp – Tomasz Kowalczyk Oct 01 '14 at 11:43
  • Therefore I suppose the training already existing in the WSR Engine will be taken into account to succesfully recognize the words spoken? It may sound silly asking, but I want to be sure that not using the default WSR program will not affect the recognition sensitivity. – Noob Doob Oct 01 '14 at 11:57

1 Answers1

1

The training is used so Windows Speech Recognition better understands what you say and gives more accurate results. This training data is stored in profiles. When you use Windows Speech Recognition in C#, you don't have to select a profile, Windows does this automatically.

ProgramFOX
  • 6,131
  • 11
  • 45
  • 51