Comments

hi everybody

when i run step 8

http://www.voxforge.org/home/dev/acousticmodels/linux/create/htkjulius/tutorial/monophones/step-8

and when i checked and reviewed the hvite_log file (the log output) i saw that  HVite did not recognize all the words for each line in your prompts file.

like with:

Aligning File: train\mfcc\sample24.mfc

Created lattice with 6 nodes / 5 arcs from label file

No tokens survived to final node of network at beam 250.0

No tokens survived to final node of network at beam 400.0

No tokens survived to final node of network at beam 550.0

SENT-END tktb mdrsaat aalkaatbaan ktb SENT-END == [261 frames] -58.3549 [Ac=-15230.6 LM=0.0] (Act=21.5)

that make my step wrong after that

 ERROR [+6510]  LOpen: Unable to open label file train/mfcc/sample24.lab
FATAL ERROR - Terminating program HERest

how i can solve that? and why this file doesnot recognise these words?

HVite -A -D -T 1 -l '*' -o SWT -b SENT-END -C config -H hmm7/macros -H hmm7/hmmdefs -i aligned.mlf -m -t 250.0 150.0 1000.0 -y lab -a -I words.mlf -S train.scp dict monophones1> HVite_log

My problem with dict file

My dict file does not contain sp at the en of each line??i do not know why? Any way if I used it in command above I get aligned.mlf but without sp???

If I add sp at each line in my dict

I got empty aligned file??

What I can do???

Another questions :why we need exactly SENT-END not silence as there in toturials?????

As i executed HVite in step 8 , the error is as follow

??? Error using ==> mtimes
Inner matrix dimensions must agree.

While executing the HVite command of step 8. I get the following error

ERROR [+5010] InitSource : Can not open source file sp

Hi

I receive the following error message when attempting to create hmm8 files using HERest command

Here is the output from HERest:

Processing Data: sample1.mfc; Label sample1.lab

 Error [+7332]  CreateInsts:  Cannot have Tee models at start or end of transcription

Can anyone tell me what is going wrong here an what I need to change in order to proceed?

Thanks

when i running

hvite -C setting/conf2.cfg -H hmm/hmm7/macros -H hmm/hmm8/hmmdefs -S data/train/train.scp -w setting/wdnet -p 0.0 -s 5.0 -l * -y lab -m -i data/test/result.mlf setting/dict.dict setting/monophones1

i got  error +8050

The dictionary file is not correctly formatted. Section 12.7 describes the HTK dictionary file format.

contain of my dict.dict 

END sil

START sil

KADO k a d o

END sil

START sil

BELA b e l a

contain of my monophones1

a

i

ee

e

o

b

p

d

t

g

k

f

z

si

kh

h

j

c

m

n

ny

ng

r

l

w

y

ai

au

ou

sil

kado

bela

sp

contain of my grammar.gra

$bebas = BELA | KADO;

(START(<$bebas>) END)

where the errors occured??

According to the Step 8:

Note: the monophone models created in hmm9 could actually be used with Julius for speech recognition, but recognition accuracy can be greatly improved by using Tied-State triphones - see next sections.

But Julius needs a file called tiedlist, when is it generated???

I get either +3219 Bad Switch END; must be single letter or +8220 LatticeFromLabels: Word SENT-END not defined in dictionary

It may happen (usually during a big mismatch between transcript and the actual speech in the recording) that no tokens reach the end of the utterence due to pruning. In that case the sentence is not included in aligned.mlf, but HTK does not report any errors. When HERest is run again, it throws an error and ends because it cannot find the transcription of the sentence in aligned.mlf.

This can be solved by switching off pruning: leave out the -t switch.

Hi,

There is a big problem with my trained hmms.

When applying the Hvite, I found there is no "sp" between two words.

I did sure that I confirm every step with its correctness, included the monophones1, pronunciation dictionary, etc.

Thanks a lot