Comments

Flat
how to discard useless result?
User: manio
Date: 5/19/2008 9:30 pm
Views: 3553
Rating: 20

Julian will find out the best fit sentence in the grammar every time I speak out,EVEN a noise happen,it will give a result.

How do I know a result is generated from a purposeful voice or a noise?

use the score1? but I found that the score of the purposeful voice and the score of the noise are nearly the same.where is the bounds?

is there another way?

thanks 

noise's result
--------------------------------------

pass1_best: <s> <n><num>1</num>ZYF</n>
pass1_best_wordseq: 0 2
pass1_best_phonemeseq: sil | jh ow r er n f aa
pass1_best_score: -10684.339844

length: 318 frames (1.06 sec.)
### Recognition: 2nd pass (RL heuristic best-first with DFA)
samplenum=318
sentence1: <s> <n><num>3</num>ZMY</n> </s>
wseq1: 0 2 1
phseq1: sil | jh aa ng m ae ng y iy | sil
cmscore1: 1.000 0.639 1.000
score1: -13599.010742
6 generated, 6 pushed, 4 nodes popped in 318

 purposeful voice
---------------------------------------------------------

pass1_best: <s> <n><num>1</num>ZYF</n>
pass1_best_wordseq: 0 2
pass1_best_phonemeseq: sil | jh ow r er n f aa
pass1_best_score: -12398.662109

length: 386 frames (1.28 sec.)
### Recognition: 2nd pass (RL heuristic best-first with DFA)
samplenum=386
sentence1: <s> <n><num>2</num>LDH</n> </s>
wseq1: 0 2 1
phseq1: sil | y ow b aa hh aa | sil
cmscore1: 1.000 1.000 1.000
score1: -14228.536133
8 generated, 8 pushed, 4 nodes popped in 386

Re: how to discard useless result?
User: kmaclean
Date: 5/20/2008 8:57 am
Views: 171
Rating: 32

Hi manio, 

>How do I know a result is generated from a purposeful voice or a noise?

See this thread, specifically the post dealing with: "creating a grammar with a few Out-of-Vocabulary words".  It talks about using an out-of-vocabulary grammar in the context of a one word grammar, but this should help in your case too. 

Another thing that might help is a better acoustic model.  This is especially important when you are trying to recognize short words (like numbers). 

If you created your own acoustic model, then you will need more training utterances.  You could also take the VoxForge acoustic model and adapt it to your voice (using your training utterances). 

You could also submit your text and speech recordings to VoxForge, or submit some speech using the speech submission application, and it will be incorporated into the VoxForge acoustic model nightly build, usually that night (but not always ...).

Ken 

Re: how to discard useless result?
User: manio
Date: 5/23/2008 10:26 pm
Views: 176
Rating: 22

thanks for your reply

I'll try it.

PreviousNext