CMU Sphinx / Forums / Help: Speech recognition using adapted model

Hi,

I have successfully adapted my model using steps given in following link http://cmusphinx.sourceforge.net/wiki/tutorialadapt
After adaptation, I have used adapted model for speech recognition using pocketsphinx_batch command

pocketsphinx_batch  -samprate 16000 -argfile argFile.txt -ctl ctlFile.txt -cepext .wav -adcin true -hyp misc/out.txt

I got the following error :-

INFO: pocketsphinx.c(145): Parsed model-specific feature parameters from /home/shashikant/KWS_Sphinx/test_sphinx/adapt_new/en-us-adapt/feat.params
Current configuration:
[NAME]          [DEFLT]     [VALUE]
-agc            none        none
-agcthresh      2.0     2.000000e+00
-allphone               
-allphone_ci        no      no
-alpha          0.97        9.700000e-01
-ascale         20.0        2.000000e+01
-aw         1       1
-backtrace      no      no
-beam           1e-48       1.000000e-48
-bestpath       yes     yes
-bestpathlw     9.5     9.500000e+00
-ceplen         13      13
-cmn            current     current
-cmninit        8.0     40,3,-1
-compallsen     no      no
-debug                  0
-dict                   /home/shashikant/KWS_Sphinx/test_sphinx/adapt_new/adapt_model/en-us-full.dict
-dictcase       no      no
-dither         no      no
-doublebw       no      no
-ds         1       1
-fdict                  /home/shashikant/KWS_Sphinx/test_sphinx/adapt_new/en-us-adapt/noisedict
-feat           1s_c_d_dd   1s_c_d_dd
-featparams             /home/shashikant/KWS_Sphinx/test_sphinx/adapt_new/en-us-adapt/feat.params
-fillprob       1e-8        1.000000e-08
-frate          100     100
-fsg                    
-fsgusealtpron      yes     yes
-fsgusefiller       yes     yes
-fwdflat        yes     yes
-fwdflatbeam        1e-64       1.000000e-64
-fwdflatefwid       4       4
-fwdflatlw      8.5     8.500000e+00
-fwdflatsfwin       25      25
-fwdflatwbeam       7e-29       7.000000e-29
-fwdtree        yes     yes
-hmm                    /home/shashikant/KWS_Sphinx/test_sphinx/adapt_new/en-us-adapt
-input_endian       little      little
-jsgf                   
-keyphrase              
-kws                    
-kws_delay      10      10
-kws_plp        1e-1        1.000000e-01
-kws_threshold      1       1.000000e+00
-latsize        5000        5000
-lda                    
-ldadim         0       0
-lifter         0       22
-lm                 /home/shashikant/KWS_Sphinx/test_sphinx/adapt_new/adapt_model/en-us-full.lm.dmp
-lmctl                  
-lmname                 
-logbase        1.0001      1.000100e+00
-logfn                  
-logspec        no      no
-lowerf         133.33334   1.300000e+02
-lpbeam         1e-40       1.000000e-40
-lponlybeam     7e-29       7.000000e-29
-lw         6.5     6.500000e+00
-maxhmmpf       30000       30000
-maxwpf         -1      -1
-mdef                   /home/shashikant/KWS_Sphinx/test_sphinx/adapt_new/en-us-adapt/mdef
-mean                   /home/shashikant/KWS_Sphinx/test_sphinx/adapt_new/en-us-adapt/means
-mfclogdir              
-min_endfr      0       0
-mixw                   /home/shashikant/KWS_Sphinx/test_sphinx/adapt_new/en-us-adapt/mixture_weights
-mixwfloor      0.0000001   1.000000e-07
-mllr                   
-mmap           yes     yes
-ncep           13      13
-nfft           512     512
-nfilt          40      25
-nwpen          1.0     1.000000e+00
-pbeam          1e-48       1.000000e-48
-pip            1.0     1.000000e+00
-pl_beam        1e-10       1.000000e-10
-pl_pbeam       1e-10       1.000000e-10
-pl_pip         1.0     1.000000e+00
-pl_weight      3.0     3.000000e+00
-pl_window      5       5
-rawlogdir              
-remove_dc      no      no
-remove_noise       yes     yes
-remove_silence     yes     yes
-round_filters      yes     yes
-samprate       16000       1.600000e+04
-seed           -1      -1
-sendump                
-senlogdir              
-senmgau                
-silprob        0.005       5.000000e-03
-smoothspec     no      no
-svspec                 
-tmat                   /home/shashikant/KWS_Sphinx/test_sphinx/adapt_new/en-us-adapt/transition_matrices
-tmatfloor      0.0001      1.000000e-04
-topn           4       4
-topn_beam      0       0
-toprule                
-transform      legacy      dct
-unit_area      yes     yes
-upperf         6855.4976   6.800000e+03
-uw         1.0     1.000000e+00
-vad_postspeech     50      50
-vad_prespeech      20      20
-vad_startspeech    10      10
-vad_threshold      2.0     2.000000e+00
-var                    /home/shashikant/KWS_Sphinx/test_sphinx/adapt_new/en-us-adapt/variances
-varfloor       0.0001      1.000000e-04
-varnorm        no      no
-verbose        no      no
-warp_params                
-warp_type      inverse_linear  inverse_linear
-wbeam          7e-29       7.000000e-29
-wip            0.65        6.500000e-01
-wlen           0.025625    2.562500e-02

INFO: feat.c(715): Initializing feature stream to type: '1s_c_d_dd', ceplen=13, CMN='current', VARNORM='no', AGC='none'
INFO: cmn.c(143): mean[0]= 12.00, mean[1..12]= 0.0
INFO: mdef.c(518): Reading model definition: /home/shashikant/KWS_Sphinx/test_sphinx/adapt_new/en-us-adapt/mdef
INFO: bin_mdef.c(181): Allocating 142124 * 8 bytes (1110 KiB) for CD tree
INFO: tmat.c(206): Reading HMM transition probability matrices: /home/shashikant/KWS_Sphinx/test_sphinx/adapt_new/en-us-adapt/transition_matrices
INFO: acmod.c(117): Attempting to use PTM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /home/shashikant/KWS_Sphinx/test_sphinx/adapt_new/en-us-adapt/means
INFO: ms_gauden.c(292): 5138 codebook, 1 feature, size: 
INFO: ms_gauden.c(294):  32x36
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /home/shashikant/KWS_Sphinx/test_sphinx/adapt_new/en-us-adapt/variances
INFO: ms_gauden.c(292): 5138 codebook, 1 feature, size: 
INFO: ms_gauden.c(294):  32x36
INFO: ms_gauden.c(354): 813 variance values floored
INFO: ptm_mgau.c(801): Number of codebooks exceeds 256: 5138
INFO: acmod.c(119): Attempting to use semi-continuous computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /home/shashikant/KWS_Sphinx/test_sphinx/adapt_new/en-us-adapt/means
INFO: ms_gauden.c(292): 5138 codebook, 1 feature, size: 
INFO: ms_gauden.c(294):  32x36
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /home/shashikant/KWS_Sphinx/test_sphinx/adapt_new/en-us-adapt/variances
INFO: ms_gauden.c(292): 5138 codebook, 1 feature, size: 
INFO: ms_gauden.c(294):  32x36
INFO: ms_gauden.c(354): 813 variance values floored
INFO: acmod.c(121): Falling back to general multi-stream GMM computation
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /home/shashikant/KWS_Sphinx/test_sphinx/adapt_new/en-us-adapt/means
INFO: ms_gauden.c(292): 5138 codebook, 1 feature, size: 
INFO: ms_gauden.c(294):  32x36
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /home/shashikant/KWS_Sphinx/test_sphinx/adapt_new/en-us-adapt/variances
INFO: ms_gauden.c(292): 5138 codebook, 1 feature, size: 
INFO: ms_gauden.c(294):  32x36
INFO: ms_gauden.c(354): 813 variance values floored
ERROR: "ms_mgau.c", line 113: Dimension of stream 0 does not match: 36 != 39
FATAL: "batch.c", line 821: PocketSphinx decoder init failed

From the error message it seem that there is mismatch between size of feature vector. But i have used same feat.params for adaptation and for testing. How this mismatch arises I could not understand?
The feat.params have following setting:-

-lowerf 130
-upperf 6800
-nfilt 25
-transform dct
-lifter 22
-feat 1s_c_d_dd
-agc none
-cmn current
-varnorm no
-cmninit 40,3,-1

Any help in this regard is most welcome...

Thanks in advance for helping me...

Speech recognition using adapted model

Speech Recognition Toolkit

Forums

Help

Speech recognition using adapted model document.SUBSCRIPTION_OPTIONS = { "thing": "topic", "subscribed": false, "url": "subscribe", "icon": { "css": "fa fa-envelope-o" } };

Speech recognition using adapted model