- This topic has 2 replies, 2 voices, and was last updated 12 years, 1 month ago by .
-
Posts
-
OK, here’s the thing.
I’d like the app to listen to an instruction like this:
“rotate 23 degrees”
Where the “23” is an arbitrary number that the user can speak. If this were a C format string, it would be “format %i degrees”, and the string returned back to me would have the number in it.
Is this possible?
Welcome,
Have you tried creating a language model which uses the number-related words you’d like to recognize? e.g. “ONE”, “TWO”, [….] , “TWENTY”, [….], “HUNDRED EIGHTY”, [….]
This is what would be necessary if you wanted to mix in numbers with other speech. If you want to recognize numbers exclusively, you’d want to replace your acoustic model with the tidigits acoustic model (and also create a language model that contains the spoken versions of the numbers you want to be able to recognize).
If the main intention of the idea is to always have a template-style sentence with variable numbers inserted in a fixed position, you want to investigate how to write JSGF rules and use a JSGF grammar with OpenEars rather than an ARPA language model.
- You must be logged in to reply to this topic.