VoxForge
VoxForge
Hi All,
I'm attempting to adapt my tied-state, context-dependent triphone system to a set of data from a novel speaker via mllr/cmll. Models have 16 mixture components, except for sil which is 32. I'm running 3.4.1 in an ubuntu environment. I'm following the guidelines given in the HTK book 3.4.1 pages 43-45.
I have no problem creating the regression tree or creating the global transform. When using the global transform as an input transform for the second pass of HERest to create either a new transform or an updated model set, I encounter a segmentation fault. Find below the results of the calls to HHEd and HERest
-------------------------------------------------------
HHEd -A -T 1 -V -D -H model/hmm13/globals -H model/hmm13/hmmdefs -M adapt adapt/regtree.hed tiedlist
No HTK Configuration Parameters Set
HTK Version Information
Module Version Who Date : CVS Info
HHEd 3.4.1 CUED 12/03/09 : $Id: HHEd.c,v 1.2 2006/12/07 11:09:08 mjfg Exp $
HShell 3.4.1 CUED 12/03/09 : $Id: HShell.c,v 1.1.1.1 2006/10/11 09:54:58 jal58 Exp $
HMem 3.4.1 CUED 12/03/09 : $Id: HMem.c,v 1.1.1.1 2006/10/11 09:54:58 jal58 Exp $
HLabel 3.4.1 CUED 12/03/09 : $Id: HLabel.c,v 1.1.1.1 2006/10/11 09:54:57 jal58 Exp $
HMath 3.4.1 CUED 12/03/09 : $Id: HMath.c,v 1.1.1.1 2006/10/11 09:54:58 jal58 Exp $
HSigP 3.4.1 CUED 12/03/09 : $Id: HSigP.c,v 1.1.1.1 2006/10/11 09:54:58 jal58 Exp $
HWave 3.4.1 CUED 12/03/09 : $Id: HWave.c,v 1.1.1.1 2006/10/11 09:54:59 jal58 Exp $
HAudio 3.4.1 CUED 12/03/09 : $Id: HAudio.c,v 1.1.1.1 2006/10/11 09:54:57 jal58 Exp $
HVQ 3.4.1 CUED 12/03/09 : $Id: HVQ.c,v 1.1.1.1 2006/10/11 09:54:59 jal58 Exp $
HModel 3.4.1 CUED 12/03/09 : $Id: HModel.c,v 1.2 2006/12/07 11:09:08 mjfg Exp $
HParm 3.4.1 CUED 12/03/09 : $Id: HParm.c,v 1.1.1.1 2006/10/11 09:54:58 jal58 Exp $
HUtil 3.4.1 CUED 12/03/09 : $Id: HUtil.c,v 1.1.1.1 2006/10/11 09:54:59 jal58 Exp $
HHEd
37443/17518 Models Loaded [5 states max, 32 mixes max]
LS stats
Loading state occupation stats
Stats loaded for 10211 models
Mean Occupation Count = 362.313977
RC 32 rtree
Building regression tree with 32 terminals
Creating regression class tree with ident rtree.tree and baseclass rtree.base
Splitting Node 1, score 9.104666e+07
Splitting Node 3, score 4.685049e+07
Splitting Node 2, score 3.131549e+07
Splitting Node 4, score 2.732998e+07
Splitting Node 7, score 1.813764e+07
Splitting Node 5, score 1.555596e+07
Splitting Node 8, score 1.510295e+07
Splitting Node 9, score 1.021550e+07
Splitting Node 6, score 1.014084e+07
Splitting Node 11, score 8.686515e+06
Splitting Node 15, score 7.892073e+06
Splitting Node 10, score 7.627271e+06
Splitting Node 12, score 7.467690e+06
Splitting Node 13, score 6.619383e+06
Splitting Node 14, score 6.289132e+06
Splitting Node 20, score 6.007492e+06
Splitting Node 18, score 5.535949e+06
Splitting Node 17, score 5.024976e+06
Splitting Node 16, score 4.456918e+06
Splitting Node 30, score 4.197672e+06
Splitting Node 27, score 4.112460e+06
Splitting Node 22, score 4.030436e+06
Splitting Node 19, score 3.639844e+06
Splitting Node 35, score 3.617287e+06
Splitting Node 28, score 3.460538e+06
Splitting Node 25, score 3.456282e+06
Splitting Node 24, score 3.371160e+06
Splitting Node 23, score 3.103943e+06
Splitting Node 32, score 2.870081e+06
Splitting Node 26, score 2.683608e+06
Splitting Node 29, score 2.571511e+06
Edit Complete
No HTK Configuration Parameters Set
HERest -A -T 1 -V -D -C model/config -C adapt/config.global -S hvite_test/test_mfc.scp -I hvite_test/cmc_wintri.mlf -H model/hmm13/globals -H model/hmm13/hmmdefs -K adapt/xforms cmllr1 -J adapt -u a -h */%%%_*.mfc tiedlist
HTK Configuration Parameters[18]
Module/Tool Parameter Value
# HMODEL TRACE 512
# HADAPT TRACE 61
# HADAPT KEEPXFORMDISTINCT TRUE
# HADAPT ADAPTKIND BASE
# HADAPT BASECLASS glob
# HADAPT USEBIAS TRUE
# HADAPT TRANSKIND MLLRMEAN
# ENORMALISE TRUE
# NUMCEPS 12
# CEPLIFTER 22
# NUMCHANS 26
# PREEMCOEF 0.970000
# USEHAMMING TRUE
# WINDOWSIZE 250000.000000
# SAVEWITHCRC TRUE
# SAVECOMPRESSED TRUE
# TARGETRATE 100000.000000
# TARGETKIND MFCC_E_D_A
HTK Version Information
Module Version Who Date : CVS Info
HERest 3.4.1 CUED 12/03/09 : $Id: HERest.c,v 1.2 2006/12/07 11:09:08 mjfg Exp $
HShell 3.4.1 CUED 12/03/09 : $Id: HShell.c,v 1.1.1.1 2006/10/11 09:54:58 jal58 Exp $
HMem 3.4.1 CUED 12/03/09 : $Id: HMem.c,v 1.1.1.1 2006/10/11 09:54:58 jal58 Exp $
HMath 3.4.1 CUED 12/03/09 : $Id: HMath.c,v 1.1.1.1 2006/10/11 09:54:58 jal58 Exp $
HSigP 3.4.1 CUED 12/03/09 : $Id: HSigP.c,v 1.1.1.1 2006/10/11 09:54:58 jal58 Exp $
HAudio 3.4.1 CUED 12/03/09 : $Id: HAudio.c,v 1.1.1.1 2006/10/11 09:54:57 jal58 Exp $
HWave 3.4.1 CUED 12/03/09 : $Id: HWave.c,v 1.1.1.1 2006/10/11 09:54:59 jal58 Exp $
HVQ 3.4.1 CUED 12/03/09 : $Id: HVQ.c,v 1.1.1.1 2006/10/11 09:54:59 jal58 Exp $
HLabel 3.4.1 CUED 12/03/09 : $Id: HLabel.c,v 1.1.1.1 2006/10/11 09:54:57 jal58 Exp $
HModel 3.4.1 CUED 12/03/09 : $Id: HModel.c,v 1.2 2006/12/07 11:09:08 mjfg Exp $
HParm 3.4.1 CUED 12/03/09 : $Id: HParm.c,v 1.1.1.1 2006/10/11 09:54:58 jal58 Exp $
HTrain 3.4.1 CUED 12/03/09 : $Id: HTrain.c,v 1.1.1.1 2006/10/11 09:54:58 jal58 Exp $
HUtil 3.4.1 CUED 12/03/09 : $Id: HUtil.c,v 1.1.1.1 2006/10/11 09:54:59 jal58 Exp $
HFB 3.4.1 CUED 12/03/09 : $Id: HFB.c,v 1.1.1.1 2006/10/11 09:54:57 jal58 Exp $
HAdapt 3.4.1 CUED 12/03/09 : $Id: HAdapt.c,v 1.2 2006/12/07 11:09:07 mjfg Exp $
HMap 3.4.1 CUED 12/03/09 : $Id: HMap.c,v 1.1.1.1 2006/10/11 09:54:57 jal58 Exp $
HERest ML Updating: XForms
System is SHARED
37443 Logical/17518 Physical Models Loaded, VecSize=39
2 MMF input files
Using baseclass macro "glob" from file adapt/glob
Attached 70672 XFormInfo structures
Attached 70669 RegAcc structures
Pruning-Off
Processing Data: cmc_1.mfc; Label cmc_1.lab
Utterance prob per frame = -6.767935e+01
Processing Data: cmc_2.mfc; Label cmc_2.lab
Utterance prob per frame = -6.676580e+01
Processing Data: cmc_3.mfc; Label cmc_3.lab
Utterance prob per frame = -6.482462e+01
Processing Data: cmc_4.mfc; Label cmc_4.lab
Utterance prob per frame = -6.825621e+01
Processing Data: cmc_5.mfc; Label cmc_5.lab
Utterance prob per frame = -6.721992e+01
Processing Data: cmc_6.mfc; Label cmc_6.lab
Utterance prob per frame = -6.683469e+01
Processing Data: cmc_7.mfc; Label cmc_7.lab
Utterance prob per frame = -6.876072e+01
Processing Data: cmc_8.mfc; Label cmc_8.lab
Utterance prob per frame = -6.697883e+01
Processing Data: cmc_9.mfc; Label cmc_9.lab
Utterance prob per frame = -6.724328e+01
Processing Data: cmc_10.mfc; Label cmc_10.lab
Utterance prob per frame = -6.706760e+01
Processing Data: cmc_11.mfc; Label cmc_11.lab
Utterance prob per frame = -6.580224e+01
Processing Data: cmc_12.mfc; Label cmc_12.lab
Utterance prob per frame = -6.688803e+01
Processing Data: cmc_13.mfc; Label cmc_13.lab
Utterance prob per frame = -6.504648e+01
Generating transform cmc (1)
Using baseclass macro "glob" from file adapt/glob
Estimated XForm 1 using 40720.329491 observations
Reestimation complete - average log prob per frame = -6.693842e+01 (40748 frames)
HTK Configuration Parameters[18]
Module/Tool Parameter Value
HMODEL TRACE 512
HADAPT TRACE 61
HADAPT KEEPXFORMDISTINCT TRUE
HADAPT ADAPTKIND BASE
HADAPT BASECLASS glob
HADAPT USEBIAS TRUE
HADAPT TRANSKIND MLLRMEAN
ENORMALISE TRUE
NUMCEPS 12
CEPLIFTER 22
NUMCHANS 26
PREEMCOEF 0.970000
USEHAMMING TRUE
WINDOWSIZE 250000.000000
SAVEWITHCRC TRUE
SAVECOMPRESSED TRUE
TARGETRATE 100000.000000
TARGETKIND MFCC_E_D_A
HERest -A -T 1 -D -V -a -C model/config -C adapt/config.rc -S hvite_test/test_mfc.scp -I hvite_test/cmc_wintri.mlf -H model/hmm13/globals -H model/hmm13/hmmdefs -J adapt/xforms cmllr1 -K adapt/xforms cmllr2 -J adapt -u a -h */%%%_*.mfc tiedlist
HTK Configuration Parameters[19]
Module/Tool Parameter Value
# HMODEL TRACE 512
# HADAPT TRACE 61
# HADAPT KEEPXFORMDISTINCT TRUE
# HADAPT SPLITTHRESH 1000.000000
# HADAPT ADAPTKIND TREE
# HADAPT REGTREE rtree.tree
# HADAPT USEBIAS TRUE
# HADAPT TRANSKIND MLLRMEAN
# ENORMALISE TRUE
# NUMCEPS 12
# CEPLIFTER 22
# NUMCHANS 26
# PREEMCOEF 0.970000
# USEHAMMING TRUE
# WINDOWSIZE 250000.000000
# SAVEWITHCRC TRUE
# SAVECOMPRESSED TRUE
# TARGETRATE 100000.000000
# TARGETKIND MFCC_E_D_A
HTK Version Information
Module Version Who Date : CVS Info
HERest 3.4.1 CUED 12/03/09 : $Id: HERest.c,v 1.2 2006/12/07 11:09:08 mjfg Exp $
HShell 3.4.1 CUED 12/03/09 : $Id: HShell.c,v 1.1.1.1 2006/10/11 09:54:58 jal58 Exp $
HMem 3.4.1 CUED 12/03/09 : $Id: HMem.c,v 1.1.1.1 2006/10/11 09:54:58 jal58 Exp $
HMath 3.4.1 CUED 12/03/09 : $Id: HMath.c,v 1.1.1.1 2006/10/11 09:54:58 jal58 Exp $
HSigP 3.4.1 CUED 12/03/09 : $Id: HSigP.c,v 1.1.1.1 2006/10/11 09:54:58 jal58 Exp $
HAudio 3.4.1 CUED 12/03/09 : $Id: HAudio.c,v 1.1.1.1 2006/10/11 09:54:57 jal58 Exp $
HWave 3.4.1 CUED 12/03/09 : $Id: HWave.c,v 1.1.1.1 2006/10/11 09:54:59 jal58 Exp $
HVQ 3.4.1 CUED 12/03/09 : $Id: HVQ.c,v 1.1.1.1 2006/10/11 09:54:59 jal58 Exp $
HLabel 3.4.1 CUED 12/03/09 : $Id: HLabel.c,v 1.1.1.1 2006/10/11 09:54:57 jal58 Exp $
HModel 3.4.1 CUED 12/03/09 : $Id: HModel.c,v 1.2 2006/12/07 11:09:08 mjfg Exp $
HParm 3.4.1 CUED 12/03/09 : $Id: HParm.c,v 1.1.1.1 2006/10/11 09:54:58 jal58 Exp $
HTrain 3.4.1 CUED 12/03/09 : $Id: HTrain.c,v 1.1.1.1 2006/10/11 09:54:58 jal58 Exp $
HUtil 3.4.1 CUED 12/03/09 : $Id: HUtil.c,v 1.1.1.1 2006/10/11 09:54:59 jal58 Exp $
HFB 3.4.1 CUED 12/03/09 : $Id: HFB.c,v 1.1.1.1 2006/10/11 09:54:57 jal58 Exp $
HAdapt 3.4.1 CUED 12/03/09 : $Id: HAdapt.c,v 1.2 2006/12/07 11:09:07 mjfg Exp $
HMap 3.4.1 CUED 12/03/09 : $Id: HMap.c,v 1.1.1.1 2006/10/11 09:54:57 jal58 Exp $
HERest ML Updating: XForms
System is SHARED
37443 Logical/17518 Physical Models Loaded, VecSize=39
2 MMF input files
Using baseclass macro "rtree.base" from file adapt/rtree.base
Using regtree macro "rtree.tree" from file adapt/rtree.tree
Attached 70672 XFormInfo structures
Attached 70669 RegAcc structures
Pruning-Off
Using input transform cmc
Using baseclass macro "glob" from file adapt/glob
Using xform macro "cmc.cmllr1" from file adapt/xforms/cmc.cmllr1
Attached 70669 AInfo structures
Created 0 ObsCaches (of 1 possible)
Attached 70672 MInfo structure
Segmentation fault (core dumped)
-------------------------------------------------------
At which point I encounter the segmentation fault...
Do you have any suggestions as to why I might be encountering this problem? Interestingly, I have succeeded with an identical process on a different language model with different phones on this same machine, so I don't believe it's an issue with the installation of HTK. I think the suspect may be the regression tree, though I'm not sure. Additionally, I've found someone else with what appears to be the same problem here.
Thanks for your time!
Eric
--- (Edited on 6/24/2015 4:48 pm [GMT-0500] by Visitor) ---
Have you tried to get any information from your core dump with gdb? That may give you some information regarding where (HERest?) failed. Your observation regarding phones may be pertinent, since it involves strings which may be badly interpreted by pointers.
--- (Edited on 2015-06-26 9:48 am [GMT-0400] by colbec) ---
Sorry for the late reply Colbec.
Running the command from within gdb:
##############
gdb /usr/local/bin/HEREst
(gdb) run -A -T 1 -D -a -C model/config -C adapt/config.rc -S scripts/mfc.scp -I data/wintri.mlf -H model/hmm13/globals -H model/hmm13/hmmdefs -M adapt -J adapt/xforms cmllr1 -J adapt -h '*/%%%%%%*_*.mfc' tiedlist
##############
Yields the output:
Program received signal SIGSEGV, Segmentation fault.
CompXForm (mp=0x7ffff78f2d20, xform=0x7ffff5a59148, ai=0x0) at HAdapt.c:2299
2299 if (ai->next != NULL) { /* There's a parent transform */
##############
calling: (gdb) where
yields:
##############
#0 CompXForm (mp=0x7ffff78f2d20, xform=0x7ffff5a59148, ai=0x0) at HAdapt.c:2299
#1 0x000000000040dff0 in ApplyHMMSetXForm (hset=<value optimized out>, xform=0x7ffff5a59148) at HAdapt.c:4112
#2 0x0000000000410a1a in UpdateSpkrStats (hset=0x7fffffffdc10, xfinfo=0x684160, datafn=0x8784a0 "./data/ral126_BR_14929.mfc") at HAdapt.c:4501
#3 0x0000000000405143 in main (argc=<value optimized out>, argv=<value optimized out>) at HERest.c:524
##############
I'm inexperienced with reading gdb output, is there anything obvious that I'm missing?
I'm fairly sure now that the fault is due to memory usage in HAdapt, but whether or not that memory usage is due to a bug or to my data is unclear. Unfortunately, the segmentation fault happens too quickly for me to monitor the memory usage via top.
Rolling back to monophones did allow the adaptation to complete successfully.
--- (Edited on 7/1/2015 2:07 pm [GMT-0500] by eric) ---
--- (Edited on 7/1/2015 2:07 pm [GMT-0500] by eric) ---
It seems to be pointing at HAdapt, on or about line 2299.
A quick google for htk hadapt 2299 does not show anything much to me, so if it is a bug it must be a very obscure one. I guess you could ask yourself what you may be doing that is way off in left field.
As we guessed, strings and pointers seem to be involved. The var ai seems to be a struct that holds a list (LIFO FIFO queue or something) that at some points to a memory location in ai->next and if next is not in the list then clunk.
Two suggestions: put the question (now that you have details) to the folks at HTK (see for example http://htk.eng.cam.ac.uk/develop/report_bug.shtml) and continue what you are doing, changing the data inputs to see if patterns emerge.
--- (Edited on 2015-07-02 4:58 pm [GMT-0400] by colbec) ---