Test Acoustic Model Using HTK
1. You need to tell HTK where all your feature vector files are
located (those are the mfcc files you created in the last step).
You do this with with a script file.
Therefore, create a file
called: test.scp
2. You also need a configuration file. Create a file called
'config ' in your 'voxforge/test' directory and add the following data:
TARGETKIND = MFCC_0_D_N_Z
TARGETRATE = 100000.0
SAVECOMPRESSED = T
SAVEWITHCRC = T
WINDOWSIZE = 250000.0
USEHAMMING = T
PREEMCOEF = 0.97
NUMCHANS = 26
CEPLIFTER = 22
NUMCEPS = 12
3. Next use HTK's HVite command to recognize the test data as follows:
a) If you created your Acoustic Model using the How-to or the the Tutorial, execute the following command:
$HVite -A -D -T 1 -H macros -H hmmdefs -C
config -S test.scp -l '*' -i recout.mlf -w wdnet -p 0.0 -s 5.0 ../lexicon/voxforge_lexicon tiedlist
b) if you Adapted the VoxForge Speaker Independent Acoustic Models
to your voice using the adaptation tutorial, the execute this command
(because you adapted using HTK
version 3.2.1, then you must use the HTK-3.2.1 version of HVite):
$/home/yourusername/htk-3.2.1/bin.linux/HVite -A -D -T 1
-H macros -H hmmdefs -C config -S test.scp -l '*' -i
recout.mlf -w wdnet -p 0.0 -s 5.0 ../lexicon/voxforge_lexicon tiedlist
This will create the following file:
recout.mlf
4. Finally, run the following command to determine the actual recognition performance of the Acoustic Model:
$HResults -I testref.mlf tiedlist recout.mlf
which will display output similar to this (note: these are results
for the 8kHz:16-bit VoxForge Speaker Independent Acoustic Model - build
396):
====================== HTK Results Analysis =======================
Date: Thu Sep 14 14:11:46 2006
Ref : testref.mlf
Rec : recout.mlf
------------------------ Overall Results --------------------------
SENT: %Correct=60.00 [H=30, S=20, N=50]
WORD: %Corr=96.83, Acc=76.19 [H=183, D=0, S=6, I=39, N=189]
===================================================================
What this means is that:
for the line starting with SENT, there were 50 test sentences and 60% were correctly recognized.
for the line starting with WORD, there were 189 words in total,
of which 96.83%
were recognized correctly. But because Julius recognized words
that are not in the audio file (i.e. insertion errors) it only gets a
76.19% accuracy rating. Count definitions:
D - Deletion Error S - Substitution Error I - Insertion Error
Comments
Click the 'Add' link to add a comment to this page.
Note: You need to be logged in to add a comment!
Search
By Mona Salem
-
3/22/2020
- 574 Replies
Read 1818 physical / 2361 logical HMMs ERROR [+8251] ReadLattice: Word A3 not in dict ERROR [+3210] DoAlignment: ReadLattice failed FATAL ERROR - Terminating program HVite
By Masoud
-
4/25/2016
- 224 Replies
I have followed the HTKbook tutorial and voxforge.org to create the HMMs. Now, I'd like to test these HMMs with the test files.
I use this command to test HMMs with some wav files
HVite -A -D -T 1 -H hmm15/macros-H hmm15/hmmdefs -C config -S test.scp -l '*' -i recout.mlf -w wdnet -p 0.0 -s 5.0 dict tiedlist
My config file like this:
TARGETKIND = MFCC_0_D_N_Z
TARGETRATE = 100000.0
SAVECOMPRESSED = T
SAVEWITHCRC = T
WINDOWSIZE = 250000.0
USEHAMMING = T
PREEMCOEF = 0.97
NUMCHANS = 26
CEPLIFTER = 22
NUMCEPS = 12
test.scp contain feature vectors of my wav files that want to test.
wdnet and dict and tiedlist make according to tutorial.
Now, when I run this command I see the belowe error.
ERROR [+3219] HVite: HMM list file name expected
FATAL ERROR - Terminating program HVite
What's this error and how can I fix it?
By bad result?
-
3/26/2016
- 262 Replies
hi
can any one help me plz?
I used the recognizer to recognise monophones model as following :
HResults -t -I testref.mlf ( tiedlist) recout.mlf
instead of (tiedlist) I used
HResults -t -I testref.mlf monophones1 recout.mlf
before this step I used gram1,wdnet1 which contain only one sentence from prompotstest.....
i defined gram1 as following :
$WORD= dubay tuxaTiTu ltazwydi rijAli AlOiTfA` biOjhzpi TyrAnK maHmwlp ;
( {SENT-START} <$WORD> {SENT-END} )
and I;ve got this bad result?
====================== HTK Results Analysis =======================
Date: Sat Mar 26 19:15:58 2016
Ref : testref1.mlf
Rec : recout1.mlf
------------------------ Overall Results --------------------------
SENT: %Correct=0.00 [H=0, S=1, N=1]
WORD: %Corr=0.00, Acc=-625.00 [H=0, D=0, S=8, I=50, N=8]
===========================
why?
By person
-
9/21/2008
- 589 Replies
In this tutorial you are doing the recognition by words. Is it is possible with the same stages to do the recognition by phoneme, of course we change the grammar and the dictionary I tried to do that but the result (recout.mlf) was only the phoneme "sil" for each sentence in test file. Is the problem that each sentence is begins and finished by a "sil" !! And the rate of recognition was 2% !!!!
How to make the decoding with the phoneme in htk?? is there a forum to do that in this site web??
please help me and thans befor