Hi,
Can anyone explain what is the relationship between grammer and vocabulary?
I have a very small set of words in a wav file (all of these are in WSJ dictionary). Would it help in decoding if I exclude the words I don't have in wav file? Right now I am using Transcriber demo with WSJ model.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
A grammar specifies the relationship of words in the vocabulary (dictionary). Recognition is essentially a graph search whic is constrained by the grammars. So reducing the size of grammar could change recognition rate and speed.
-a
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi,
Can anyone explain what is the relationship between grammer and vocabulary?
I have a very small set of words in a wav file (all of these are in WSJ dictionary). Would it help in decoding if I exclude the words I don't have in wav file? Right now I am using Transcriber demo with WSJ model.
A grammar specifies the relationship of words in the vocabulary (dictionary). Recognition is essentially a graph search whic is constrained by the grammars. So reducing the size of grammar could change recognition rate and speed.
-a