VoxForge
VoxForge
--- (Edited on 6/11/2007 3:20 am [GMT-0500] by nagi) ---
Hi Nagi,
1. "hmmdefs" file created in "hmm12"
>Warning: more than one arc to end state
>Warning: HMM
"sp" has unsupported arc.
I got the same error when running the Julian ... you would likely need to recompile Julius with the configure option "--enable-multipath" - see Ticket #2 for an explanation.
>Error: HMMList: line 2: physical HMM "C" not
found
>....
>....
>Error: HMMList: line 2631:
physical HMM "Y" not found
>Error: HMMList: line
2661: physical HMM "er" not found
>HMMList
"../phone_m/tiedlist" read error
You should use the "triphones1" file you created in step 10. Your "tiedlist" file was created in step 11 and contains mappings from logical triphones (the "unseen" triphones) to the physical triphones. I don't think you can use it with the Acoustic Models you created in step 10. You may also need to copy the contents of your monophones1 from Step 2 to the triphones1 file for this to work.
2. "hmmdefs" file created in "hmm15"
>Does anybody know what is wrong with my Acoustic modell ?
Is the phoneme list in your pronunciation dictionary the same as what is in your hmmdefs file?
are you using 2-gram and reverse 3-gram language model? See this post for more information.
Hope this helps,
Ken
--- (Edited on 6/11/2007 2:38 pm [GMT-0400] by kmaclean) ---
--- (Edited on 6/13/2007 6:14 am [GMT-0500] by nagi) ---
Hi Nagi,
What is in your pronunciation dictionary for the word "ZWOELF" - what is the list of phonemes for this word? ... is there a spelling mistake in the phonemes for this word and the only phone for this word is 'sp' or 'sil'?
From LEE Akinobu (in Ticket # 2):
KenPlease note that, even with the "multi-path version", Julius does not allow a definition of a word in which all phone HMM have such "whole model-skip transition", because it requires word-level skipping and hard to handle at decoding process. For example, if you have "sp" model with model-skipping transition, you can attach or insert the sp model to any position of other words in the dictionary, but you can not define a word with only the "sp" model. In such case, Julius/Julian outputs error.
--- (Edited on 6/13/2007 10:01 am [GMT-0400] by kmaclean) ---
--- (Edited on 6/14/2007 3:08 am [GMT-0500] by Visitor) ---
Hi Nagi,
Glad you got Julius to work!
With respect to HTK's word insertion penalties (-p) and grammar scale factor (-s), the HTK book says the following:
The word insertion penalty is a ?xed value added to each token when it transits from the end of one word to the start of the next.
The grammar scale factor is the amount by which the language model probability is scaled before being added to each token as it transits from the end of one word to the start of the next.
Julian uses the following parameters (these parameters are not available in Julius):
-penalty1 :Word insertion penalty for the first pass. (default: 0.0)
-penalty2 : Word insertion penalty for the second pass. (default: 0.0)
Julius uses the following (these parameters are not available in Julian):
-lmp lm_weight lm_penalty
-lmp2 lm_weight2 lm_penalty2Language model score weights and word insertion penalties for the first and second passes respectively.
I have not used the Julius language model penalties. Most of my experience is with Julian, and I determined the proper word insertion penalties after a lot of experimentation. I created a test set and ran the the acoustic model against the test set until I got optimal results.
Julius and Julian also have the -iwsppenalty parameter (only seems to be documented in the config file):
## For insertion of context-free short-term inter-word pauses between words
## (multi-path version only)
##
-iwsp # append a skippable sp model at all word ends
-iwsppenalty -70.0 # transition penalty for the appended sp models
I have not played with the Julian -penalty1, -penalty2, -iwsppenalty parameters very much, but it seems like if I add new audio to an Acoustic Model, these parameters must be tweaked to get the best recognition results.
Ken
--- (Edited on 6/14/2007 10:19 am [GMT-0400] by kmaclean) ---