>Is it possible to make an acoustic model just with this two phrases?

Yes, but why?

>And if it is, will this improve the recognition of this two phrases?

No necessarily.  See this post for the reasons why:One word grammar, always recognized? (the later posts) which says:

It seems like Julian returns the best fit for whatever grammar you have, and if you have a one word grammar that means returning that single word every time.

[...]

As a workaround, you might try creating a grammar with a few Out-of-Vocabulary words, in addition to the word you want to recognize, and then use your application to determine if your target word gets recognized. 

tpvelka indicates in ths post: Whole-Word Recognition that:

Whole word HMM are usefull if you want to do IWR and do not have enough training data. Otherwise, just use phoneme HMM (i.e. the standard described in all tutorials).

Ken

--- (Edited on 7/14/2009 9:51 am [GMT-0400] by kmaclean) ---

Thank you Ken,

So I wouldn't get any improvement.

Is there any way to adapt the model as it is said in this tutorial http://www.voxforge.org/home/dev/acousticmodels/linux/adapt, but only recording those phrases.


Thak you

--- (Edited on 7/15/2009 10:30 am [GMT-0500] by Visitor) ---

>Is there any way to adapt the model as it is said in this tutorial

>http://www.voxforge.org/home/dev/acousticmodels/linux/adapt, but only

>recording those phrases.

This should work (no guarantees - I have not tried adaptation with so little of speech):

• Create a prompts file as per Step 2 in the AM training Tutorial (you do not need to create a wlist file or pronunciation dictionary);
• record you prompts as described in Step 3 of the AM training Tutorial, but at 8000Hz-8bits (so you can skip the downsample step in Step 1 of the AM adapting tutorial);
• manually create an MLF file in the same format as the mlf in Step 4 of the AM training Tutorial, for each of our two speech sentences;
  
• in Step 2 of the AM adapting tutorial, only include the two speech files you recorded in your codetrain.scp;
  
• continue with the rest of the adaptation tutorial.

This assume you have downloaded HTK v3.2.1.

Ken

--- (Edited on 7/20/2009 1:07 pm [GMT-0400] by kmaclean) ---