VoxForge & Julius Quick Start - Julius Grammar

The enclosed sample grammar files are for demonstration purposes only.  They 
allow the Julius speech recognition engine to recognize the following type of
sentences (and many more):

 * CALL STEVE YOUNG
 * DIAL FIVE SEVEN EIGHT TWO
 * DIAL THREE ZERO 
 * DIAL TWO TWO FOUR FOUR NINE ZERO SEVEN SEVEN 
 * PHONE JOE YOUNG JOHNSTON JOHNSTON JOHNSTON STEVE STEVE STEVE JOE 
 * CALL BOB JORDAN
 * CALL STEVE
 * CALL STEVE JOHNSTON
 * PHONE STEVE 
 * DIAL OH OH FOUR FIVE SIX 

Basically, the grammar is designed to recognize any combination of the numbers 
1 through 9, ZERO and OH.  You must precede numbers with the word 'DIAL' - as
in "dial 1 2 3".  

It is also set up to recognize any combination of the following names: STEVE, 
YOUNG, BOB, JOHNSTON, JOHN, JORDAN, and JOE.  You must precede the names with
the words "PHONE" or "CALL" - as in "phone steve young" or "call johnston".

You can add any word from the VoxForge dictionary (VoxForgeDict.txt) to your
sample.voca file and recompile the Julius grammar using the included mkdfa.pl
script (Perl).

For help with Julius grammar syntax see 
 * the VoxForge tutorial step 1 at: 
 
    http://www.voxforge.org/home/dev/acousticmodels/linux/create/htkjulius/tutorial/data-prep/step-1 
    
  - or -
  
 * the Julius grammar tutorial on the Julius web site at: 
 
    http://julius.sourceforge.jp/en_index.php?q=en_grammar.html

If you want to add words not included in to your grammar, you can only use the words (and 
phones) contained in the VoxForge Dictionary.  This was the dictionary used to
train the acoustic model you are using.  

If you want to use words that are not included in this dictionary, you may need 
to recompile the acoustic model with audio that uses the words you want to add.  
The VoxForge how-to and tutorial can walk you the steps required to do this, 
see our web site at: 

  http://www.voxforge.org/home/dev/acousticmodels

Remember, your recognition quality will be only as good as the Acoustic Model you use, 
and we need many more speech submisisons create decent quality Acoustic Models.  
So please take the time to submit some speech to www.voxforge.org.

thank you,

VoxForge.
