Comments

If you have a small grammar, the following things can help improve recognition performance:

• using a noise model,
• using word-based hmm with more states (rather than phone-based hmm),
• not using context-independent models

please help me, I need to know how to tied acoustic modle with java application

please repliy me as fast as you can because i have to deliver the project after a five days

Thanks for this tutorial ,i tried to execute acoustic model but i finished it but i have remark

when i record audio by 48kHZ and all steps i do it but in running julian it can recognize some words and other nooooo

and the speed for it very high and it output words which i not speech thats beacause what mic not good or julian have high speed

thanks 

Hi,

        I had successful develop HTK speech recognition application based on the tutorial given here. I would like to know after speak 'Phone Steve' in Julius, where in the result below I can find the recognition rate or percentage? Can I know where is the final recognition result that show the recognition rate(%) after it successfully recognize 'Phone Steve' as a speak sentence?

=======================================

pass1_best: <s> PHONE STEVE
pass1_best_wordseq: 0 2 4
pass1_best_phonemeseq: sil | f ow n | s t iy v
pass1_best_score: -4077.380615

length: 155 frames (1.55 sec.)
### Recognition: 2nd pass (RL heuristic best-first with DFA)
samplenum=155
stack empty, search terminate now
2 sentences have found
sentence1: <s> PHONE STEVE </s>
wseq1: 0 2 4 1
phseq1: sil | f ow n | s t iy v | sil
cmscore1: 1.000 1.000 0.893 1.000
score1: -4082.822754
20 generated, 20 pushed, 22 nodes popped in 155
recorded to "recording/2006.0222.234955.wav" (50130 bytes, 1.57 sec.)
=======================================

Besides that, I would like to know if any reference of code/tutorial/application that act as dialogue system. After HVite command the application will reply some text/message?

Example: Speak---> Phone Steve

System reply ------> Please wait. Calling.

Thank you.

Regards,

Cecifia

whe i tried to excute the command julian -input mic -C julian.jconf,nothing is displayed.That means no error,warning as well as correct messages at all. So, what is the problem.

Is there anyone to help me

Hi, I have a problem with run a Julian. When I run it, I get this message:

include config: julian.conf
julian: failed to open jconf file: julian.conf
Terminated

Please, help me. Thanks.

Hi,

I've got a problem when I try to run Julius-4.1.2 as Julian! I always get this warning massage:

...

------
### read waveform input
STAT: AD-in thread created
<<< please speak >>>Warning: strip: sample 0-21 has zero value, stripped

When I use the Julian Version from Julius-3.5.2 then I don't get this massage and it works wonderfull!

In my julius-4.1.2 config file I picked the following options:

-dfa sample.dfa  -v sample.dict  -h hmm15/hmmdefs  -hlist ./tiedlist  -iwcd1 max  -gprune safe  -b2 200  -sb 200.0 -spmodel "sp"  -iwsp  -iwsppenalty -70.0  -input mic

Does anybody know where this massage comes from and how to correct the mistake?

Regards, Nick

Hi,

I'm trying to use the newest Julius Version 4.1.2 (from http://julius.sourceforge.jp/en_index.php?q=index-en.html#get_current_ver)  as Julian!

Is that possible? I can't find a Julian executable in the Julius-4.1.2 folder! Can anybody tell me how to make that version run as Julian?

So far I'm using the julius-3.5.2 version from the voxforge site!

Best regards, Nick

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

Thanhs a lot for this tutorial,

It is a really good help to start using SRE.

I do the tutorial and in fact I am not really satisfied of the Julian Result. He recognize less than one sentence on four.

Quite bad result no.

I record the sample using audacity at a sample rate of 98000Hz. Maybe it is the cause of my problem, what do do think ?

But I don't forget to change the sampling rate in Jconf.

What shoulld I do to improve the recognition.

THX

Fab

First of all, I say thanks a lot for your help before. I am really supported by your answers on my questions. Now, I have already trained several Indonesian audio files to get hmm models. Then, I get language model, that is 2-gram language model (ARPA format), by using a tool provided in "http://www.speech.cs.cmu.edu/tools/lm.html".

I use all of those models, acoustic model and language model, with Julius to test some speech. The content of jconf file (julius.jconf) I use is:

-nlr model/grammar
-v dict
-h hmm15/hmmdefs
-hlist tiedlist
-gprune safe     
-input rawfile        # ‰¹�º”gŒ`ƒf�[ƒ^ƒtƒ@ƒCƒ‹(ƒtƒH�[ƒ}ƒbƒg�©“®”»•Ê)

            # Œ`�®�FWAV(16bit) ‚Ü‚½‚Í
            #    RAW(16bit(signed short),mono,big-endian) 
            #    16kHzˆÈŠO‚̃tƒ@ƒCƒ‹‚Í -smpFreq ‚Å�ü”g�”�w’è
-filelist listfile.txt    # ”F�¯‘Î�Ûƒtƒ@ƒCƒ‹‚̃ŠƒXƒg
-smpFreq 16000        # ƒTƒ“ƒvƒŠƒ“ƒO�ü”g�”(Hz)
-smpPeriod 625    # ƒTƒ“ƒvƒŠƒ“ƒO�üŠú(ns) (= 10000000 / smpFreq)
-demo            # "-progout -quiet" ‚Æ“¯

When I run Julius by typing: "julius -C julius.jconf", there are errors (I show you the whole results) as follows:

$ julius -C julius.jconf
STAT: include config: julius.jconf
STAT: jconf successfully finalized
STAT: *** loading AM00 _default
Stat: init_phmm: Reading in HMM definition
Stat: rdhmmdef: ascii format HMM definition
Stat: rdhmmdef: limit check passed
Stat: check_hmm_restriction: an HMM with several arcs from initial state found:
"sp"
Stat: rdhmmdef: this HMM requires multipath handling at decoding
Stat: init_phmm: defined HMMs:    23
Stat: init_phmm: logical names:   117 in HMMList
Stat: init_phmm: base phones:    23 used in logical
Stat: init_phmm: finished reading HMM definitions
STAT: making pseudo bi/mono-phone for IW-triphone
Stat: hmm_lookup: 92 pseudo phones are added to logical HMM list
STAT: *** AM00 _default loaded
STAT: *** loading LM00 _default
Stat: init_voca: read 23 words
Stat: init_ngram: reading in ARPA forward n-gram from model/grammar
Stat: ngram_read_arpa: this is 2-gram file
Stat: ngram_read_arpa: reading 1-gram part...
Stat: ngram_read_arpa: read 19 1-gram entries
Stat: ngram_read_arpa: reading 2-gram part...
Stat: ngram_read_arpa: 2-gram read 0 (0%)
Stat: ngram_read_arpa: 2-gram read 32 end
Stat: ngram_compact_context: bigram bowt compaction: 32 -> 0
Error: mymalloc: failed to reallocate 0 bytes

Before that, I have also experienced "Error: ngram_compact_context: 2-gram has no upper 3-gram, but not 0.0 back-off w
eight".

Could you help me to solve those two errors? Thanks a lot.

regards,

Amalia zahra 

I have prepared all model needed to run Julius. The contents of jconf file (julius.jconf) to run julius are:

-nlr model/grammar        # 2-gram
-v dict
-h hmm15/hmmdefs
-hlist tiedlist
-gprune safe        # safe pruning �ãˆÊNŒÂ‚ªŠm�À‚É‹�‚Ü‚é�D�³Šm�D
-n 10
-output 10        # ‘æ2ƒpƒX‚ÅŒ©‚‚©‚Á‚½•¶‚Ì‚¤‚¿�o—Í‚·‚é�” �i•¶�”�j
-input rawfile        # ‰¹�º”gŒ`ƒf�[ƒ^ƒtƒ@ƒCƒ‹(ƒtƒH�[ƒ}ƒbƒg�©“®”»•Ê)
            # Œ`�®�FWAV(16bit) ‚Ü‚½‚Í
            #    RAW(16bit(signed short),mono,big-endian) 
            #    16kHzˆÈŠO‚̃tƒ@ƒCƒ‹‚Í -smpFreq ‚Å�ü”g�”�w’è
-filelist listfile.txt    # ”F�¯‘Î�Ûƒtƒ@ƒCƒ‹‚̃ŠƒXƒg
-zmean            # DC�¬•ª‚Ì�œ‹�‚ð�s‚¤ (-input mfcfile��–³Œø)
-rejectshort 100    # �w’èƒ~ƒŠ•bˆÈ‰º‚Ì’·‚³‚Ì“ü—Í‚ðŠü‹p‚·‚é
-lv 10000        # ƒŒƒxƒ‹‚Ì‚µ‚«‚¢’l (0-32767)
-smpFreq 16000        # ƒTƒ“ƒvƒŠƒ“ƒO�ü”g�”(Hz)
-smpPeriod 625    # ƒTƒ“ƒvƒŠƒ“ƒO�üŠú(ns) (= 10000000 / smpFreq)
-demo            # "-progout -quiet" ‚Æ“¯‚¶ 

When I run julius by typing:

$julius -C julius.jconf 

There were errors as follows:

STAT: include config: julius.jconf
STAT: jconf successfully finalized
STAT: *** loading AM00 _default
Stat: init_phmm: Reading in HMM definition
Stat: rdhmmdef: ascii format HMM definition
Stat: rdhmmdef: limit check passed
Stat: check_hmm_restriction: an HMM with several arcs from initial state found:
"sp"
Stat: rdhmmdef: this HMM requires multipath handling at decoding
Stat: init_phmm: defined HMMs:    17
Stat: init_phmm: logical names:    46 in HMMList
Stat: init_phmm: base phones:    17 used in logical
Stat: init_phmm: finished reading HMM definitions
STAT: making pseudo bi/mono-phone for IW-triphone
Stat: hmm_lookup: 28 pseudo phones are added to logical HMM list
STAT: *** AM00 _default loaded
STAT: *** loading LM00 _default
Error: voca_load_htkdict: line 1: triphone "uh-ah+sp" not found
Error: voca_load_htkdict: line 1: triphone "ah-sp+*" or biphone "ah-sp" not foun
d
Error: voca_load_htkdict: the line content was: DUA             [DUA]
d uh ah sp
Error: voca_load_htkdict: line 2: triphone "ah-t+sp" not found
Error: voca_load_htkdict: line 2: triphone "t-sp+*" or biphone "t-sp" not found
Error: voca_load_htkdict: the line content was: EMPAT           [EMPAT]
ax m p ah t sp
Error: voca_load_htkdict: line 3: triphone "ah-m+sp" not found
Error: voca_load_htkdict: line 3: triphone "m-sp+*" or biphone "m-sp" not found
Error: voca_load_htkdict: the line content was: ENAM            [ENAM]
ax n ah m sp
Error: voca_load_htkdict: line 4: triphone "oh-ng+sp" not found
Error: voca_load_htkdict: line 4: triphone "ng-sp+*" or biphone "ng-sp" not foun
d
Error: voca_load_htkdict: the line content was: KOSONG          [KOSONG]
k oh sh oh ng sp
Error: voca_load_htkdict: line 5: triphone "m-ah+sp" not found
Error: voca_load_htkdict: line 5: triphone "ah-sp+*" or biphone "ah-sp" not foun
d
Error: voca_load_htkdict: the line content was: LIMA            [LIMA]
l ih m ah sp
Error: voca_load_htkdict: line 6: triphone "t-uh+sp" not found
Error: voca_load_htkdict: line 6: triphone "uh-sp+*" or biphone "uh-sp" not foun
d
Error: voca_load_htkdict: the line content was: SATU            [SATU]
sh ah t uh sp
Error: voca_load_htkdict: line 9: triphone "g-ah+sp" not found
Error: voca_load_htkdict: line 9: triphone "ah-sp+*" or biphone "ah-sp" not foun
d
Error: voca_load_htkdict: the line content was: TIGA            [TIGA]
t ih g ah sp
Error: voca_load_htkdict: begin missing phones
Error: voca_load_htkdict: ah-m+sp
Error: voca_load_htkdict: ah-sp+* or biphone ah-sp
Error: voca_load_htkdict: ah-t+sp
Error: voca_load_htkdict: g-ah+sp
Error: voca_load_htkdict: m-ah+sp
Error: voca_load_htkdict: m-sp+* or biphone m-sp
Error: voca_load_htkdict: ng-sp+* or biphone ng-sp
Error: voca_load_htkdict: oh-ng+sp
Error: voca_load_htkdict: t-sp+* or biphone t-sp
Error: voca_load_htkdict: t-uh+sp
Error: voca_load_htkdict: uh-ah+sp
Error: voca_load_htkdict: uh-sp+* or biphone uh-sp
Error: voca_load_htkdict: end missing phones
Error: init_voca: error in reading dict: 7 words failed out of 2 words
ERROR: m_fusion: failed to read dictionary, terminated
ERROR: m_fusion: failed to initialize dictionary
ERROR: Error in loading model 

I knew that those missing phones didn't exist in "triphones1" file, but this file was generated by HTKToolkit. I think this problem occurs because of the content of "dict" file that consists of list of words like this: "DUA             [DUA]           d uh ah sp", which is generated by HTKToolkit and already consists of "sp". Can you help me to solve this problem? Thank you very much.

regards,

Amalia Zahra   

Need to review creation of sp hmm in  Step 7 - Fixing the Silence Models to figure out why this error is appearing:

Warning: HMM "sp" has unsupported arc.
SERIOUS WARNING: Transition arc has been modified as below
SERIOUS WARNING: This may cause unintended recognition result

Seems to have no noticeable effect on recognition.

Ken