Hi, I'm very new to Pocketsphinx and voice recognition in general... I would like to handle a grammar involving numbers between 1-1000. Is this possible and if it, what is the best way to achieve this?
I have a JSGF grammar that's basically like this: public <item> = <sport> <number1-1000> <unit>;
So a person should be able to say this:
"Soccer 4 goals"
"Dart 995 points"
I don't know how I'm supposed to handle numbers though.
Currently I'm thinking like this: Add all combinations to my dictionary like:
"one two three .... twenty, thirty ... one hundred two hundred ...."
Create a grammar from this so when a person say "995", recognizer recognizes these 3 combinations:
"nine hundred, ninty, five".
Is there a better solution?
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi, I'm very new to Pocketsphinx and voice recognition in general... I would like to handle a grammar involving numbers between 1-1000. Is this possible and if it, what is the best way to achieve this?
I have a JSGF grammar that's basically like this:
public <item> = <sport> <number1-1000> <unit>;So a person should be able to say this:
I don't know how I'm supposed to handle numbers though.
Currently I'm thinking like this: Add all combinations to my dictionary like:
Create a grammar from this so when a person say "995", recognizer recognizes these 3 combinations:
Is there a better solution?
No