CMUSphix не распознает

Я пытаюсь проверить работу библиотеки CMUSphinx под Windows.
Я проверяю учебник в http://cmusphinx.sourceforge.net/wiki/tutorialpocketsphinx
и собрать библиотеку sphinxbase и pokectsphinx.

Затем я пытаюсь проверить работоспособность встроенной библиотеки и запустить приложение pocketsphinx_continuous.exe со следующими параметрами:

C:\Users\admin>D:\Work\Elis\Win32\pocketsphinx-0.8-win32\bin\Release\pocketsphinx_continuous.exe -hmm d:\Work\Elis\Win32\pocketsphinx-0.8-win32\model\hm
m\en_US\hub4wsj_sc_8k -dic d:\Work\Elis\Win32\pocketsphinx-0.8-win32\model\lm\en
_US\cmu07a.dic -lm d:\Work\Elis\Win32\pocketsphinx-0.8-win32\model\lm\en_US\wsj0
vp.5000.DMP

После этого в консоли я вижу следующее:

INFO: cmd_ln.c(691): Parsing command line:
D:\Work\Elis\Win32\pocketsphinx-0.8-win32\bin\Release\pocketsphinx_continuous.ex
e \
-hmm d:\Work\Elis\Win32\pocketsphinx-0.8-win32\model\hmm\en_US\hub4wsj_s
c_8k \
-dic d:\Work\Elis\Win32\pocketsphinx-0.8-win32\model\lm\en_US\cmu07a.dic
\
-lm d:\Work\Elis\Win32\pocketsphinx-0.8-win32\model\lm\en_US\wsj0vp.5000
.DMP

Current configuration:
[NAME]          [DEFLT]         [VALUE]
-adcdev
-agc            none            none
-agcthresh      2.0             2.000000e+000
-alpha          0.97            9.700000e-001
-argfile
-ascale         20.0            2.000000e+001
-aw             1               1
-backtrace      no              no
-beam           1e-48           1.000000e-048
-bestpath       yes             yes
-bestpathlw     9.5             9.500000e+000
-bghist         no              no
-ceplen         13              13
-cmn            current         current
-cmninit        8.0             8.0
-compallsen     no              no
-debug                          0
-dict
-dictcase       no              no
-dither         no              no
-doublebw       no              no
-ds             1               1
-fdict
-feat           1s_c_d_dd       1s_c_d_dd
-featparams
-fillprob       1e-8            1.000000e-008
-frate          100             100
-fsg
-fsgusealtpron  yes             yes
-fsgusefiller   yes             yes
-fwdflat        yes             yes
-fwdflatbeam    1e-64           1.000000e-064
-fwdflatefwid   4               4
-fwdflatlw      8.5             8.500000e+000
-fwdflatsfwin   25              25
-fwdflatwbeam   7e-29           7.000000e-029
-fwdtree        yes             yes
-hmm                            d:\Work\Elis\Win32\pocketsphinx-0.8-win32\model\
hmm\en_US\hub4wsj_sc_8k
-infile
-input_endian   little          little
-jsgf
-kdmaxbbi       -1              -1
-kdmaxdepth     0               0
-kdtree
-latsize        5000            5000
-lda
-ldadim         0               0
-lextreedump    0               0
-lifter         0               0
-lm                             d:\Work\Elis\Win32\pocketsphinx-0.8-win32\model\
lm\en_US\wsj0vp.5000.DMP
-lmctl
-lmname         default         default
-logbase        1.0001          1.000100e+000
-logfn
-logspec        no              no
-lowerf         133.33334       1.333333e+002
-lpbeam         1e-40           1.000000e-040
-lponlybeam     7e-29           7.000000e-029
-lw             6.5             6.500000e+000
-maxhmmpf       -1              -1
-maxnewoov      20              20
-maxwpf         -1              -1
-mdef
-mean
-mfclogdir
-min_endfr      0               0
-mixw
-mixwfloor      0.0000001       1.000000e-007
-mllr
-mmap           yes             yes
-ncep           13              13
-nfft           512             512
-nfilt          40              40
-nwpen          1.0             1.000000e+000
-pbeam          1e-48           1.000000e-048
-pip            1.0             1.000000e+000
-pl_beam        1e-10           1.000000e-010
-pl_pbeam       1e-5            1.000000e-005
-pl_window      0               0
-rawlogdir
-remove_dc      no              no
-round_filters  yes             yes
-samprate       16000           1.600000e+004
-seed           -1              -1
-sendump
-senlogdir
-senmgau
-silprob        0.005           5.000000e-003
-smoothspec     no              no
-svspec
-time           no              no
-tmat
-tmatfloor      0.0001          1.000000e-004
-topn           4               4
-topn_beam      0               0
-toprule
-transform      legacy          legacy
-unit_area      yes             yes
-upperf         6855.4976       6.855498e+003
-usewdphones    no              no
-uw             1.0             1.000000e+000
-var
-varfloor       0.0001          1.000000e-004
-varnorm        no              no
-verbose        no              no
-warp_params
-warp_type      inverse_linear  inverse_linear
-wbeam          7e-29           7.000000e-029
-wip            0.65            6.500000e-001
-wlen           0.025625        2.562500e-002

INFO: cmd_ln.c(691): Parsing command line:
\
-nfilt 20 \
-lowerf 1 \
-upperf 4000 \
-wlen 0.025 \
-transform dct \
-round_filters no \
-remove_dc yes \
-svspec 0-12/13-25/26-38 \
-feat 1s_c_d_dd \
-agc none \
-cmn current \
-cmninit 56,-3,1 \
-varnorm no

Current configuration:
[NAME]          [DEFLT]         [VALUE]
-agc            none            none
-agcthresh      2.0             2.000000e+000
-alpha          0.97            9.700000e-001
-ceplen         13              13
-cmn            current         current
-cmninit        8.0             56,-3,1
-dither         no              no
-doublebw       no              no
-feat           1s_c_d_dd       1s_c_d_dd
-frate          100             100
-input_endian   little          little
-lda
-ldadim         0               0
-lifter         0               0
-logspec        no              no
-lowerf         133.33334       1.000000e+000
-ncep           13              13
-nfft           512             512
-nfilt          40              20
-remove_dc      no              yes
-round_filters  yes             no
-samprate       16000           1.600000e+004
-seed           -1              -1
-smoothspec     no              no
-svspec                         0-12/13-25/26-38
-transform      legacy          dct
-unit_area      yes             yes
-upperf         6855.4976       4.000000e+003
-varnorm        no              no
-verbose        no              no
-warp_params
-warp_type      inverse_linear  inverse_linear
-wlen           0.025625        2.500000e-002

INFO: acmod.c(246): Parsed model-specific feature parameters from d:\Work\Elis\W
in32\pocketsphinx-0.8-win32\model\hmm\en_US\hub4wsj_sc_8k/feat.params
INFO: feat.c(713): Initializing feature stream to type: '1s_c_d_dd', ceplen=13,
CMN='current', VARNORM='no', AGC='none'
INFO: cmn.c(142): mean[0]= 12.00, mean[1..12]= 0.0
INFO: acmod.c(167): Using subvector specification 0-12/13-25/26-38
INFO: mdef.c(517): Reading model definition: d:\Work\Elis\Win32\pocketsphinx-0.8
-win32\model\hmm\en_US\hub4wsj_sc_8k/mdef
INFO: mdef.c(528): Found byte-order mark BMDF, assuming this is a binary mdef fi
le
INFO: bin_mdef.c(336): Reading binary model definition: d:\Work\Elis\Win32\pocke
tsphinx-0.8-win32\model\hmm\en_US\hub4wsj_sc_8k/mdef
INFO: bin_mdef.c(513): 50 CI-phone, 143047 CD-phone, 3 emitstate/phone, 150 CI-s
en, 5150 Sen, 27135 Sen-Seq
INFO: tmat.c(205): Reading HMM transition probability matrices: d:\Work\Elis\Win
32\pocketsphinx-0.8-win32\model\hmm\en_US\hub4wsj_sc_8k/transition_matrices
INFO: acmod.c(121): Attempting to use SCHMM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: d:\Work\Elis\Win32\p
ocketsphinx-0.8-win32\model\hmm\en_US\hub4wsj_sc_8k/means
INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:
INFO: ms_gauden.c(294):  256x13
INFO: ms_gauden.c(294):  256x13
INFO: ms_gauden.c(294):  256x13
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: d:\Work\Elis\Win32\p
ocketsphinx-0.8-win32\model\hmm\en_US\hub4wsj_sc_8k/variances
INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:
INFO: ms_gauden.c(294):  256x13
INFO: ms_gauden.c(294):  256x13
INFO: ms_gauden.c(294):  256x13
INFO: ms_gauden.c(354): 0 variance values floored
INFO: s2_semi_mgau.c(903): Loading senones from dump file d:\Work\Elis\Win32\poc
ketsphinx-0.8-win32\model\hmm\en_US\hub4wsj_sc_8k/sendump
INFO: s2_semi_mgau.c(927): BEGIN FILE FORMAT DESCRIPTION
INFO: s2_semi_mgau.c(1022): Using memory-mapped I/O for senones
INFO: s2_semi_mgau.c(1296): Maximum top-N: 4 Top-N beams: 0 0 0
INFO: dict.c(317): Allocating 4107 * 20 bytes (80 KiB) for word entries
INFO: dict.c(341): Reading filler dictionary: d:\Work\Elis\Win32\pocketsphinx-0.
8-win32\model\hmm\en_US\hub4wsj_sc_8k/noisedict
INFO: dict.c(211): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(344): 11 words read
INFO: dict2pid.c(396): Building PID tables for dictionary
INFO: dict2pid.c(404): Allocating 50^3 * 2 bytes (244 KiB) for word-initial trip
hones
INFO: dict2pid.c(131): Allocated 30200 bytes (29 KiB) for word-final triphones
INFO: dict2pid.c(195): Allocated 30200 bytes (29 KiB) for single-phone word trip
hones
INFO: ngram_model_arpa.c(77): No \data\ mark in LM file
INFO: ngram_model_dmp.c(142): Will use memory-mapped I/O for LM file
INFO: ngram_model_dmp.c(196): ngrams 1=5002, 2=338656, 3=291318
INFO: ngram_model_dmp.c(242):     5002 = LM.unigrams(+trailer) read
INFO: ngram_model_dmp.c(288):   338656 = LM.bigrams(+trailer) read
INFO: ngram_model_dmp.c(314):   291318 = LM.trigrams read
INFO: ngram_model_dmp.c(339):    32470 = LM.prob2 entries read
INFO: ngram_model_dmp.c(359):    13795 = LM.bo_wt2 entries read
INFO: ngram_model_dmp.c(379):    31136 = LM.prob3 entries read
INFO: ngram_model_dmp.c(407):      662 = LM.tseg_base entries read
INFO: ngram_model_dmp.c(463):     5002 = ascii word strings read
INFO: ngram_search_fwdtree.c(99): 0 unique initial diphones
INFO: ngram_search_fwdtree.c(147): 0 root, 0 non-root channels, 12 single-phone
words
INFO: ngram_search_fwdtree.c(186): Creating search tree
INFO: ngram_search_fwdtree.c(191): before: 0 root, 0 non-root channels, 12 singl
e-phone words
INFO: ngram_search_fwdtree.c(326): after: max nonroot chan increased to 128
ERROR: "ngram_search_fwdtree.c", line 336: No word from the language model has p
ronunciation in the dictionary
INFO: ngram_search_fwdtree.c(338): after: 0 root, 0 non-root channels, 11 single
-phone words
INFO: ngram_search_fwdflat.c(156): fwdflat: min_ef_width = 4, max_sf_win = 25
INFO: continuous.c(371): D:\Work\Elis\Win32\pocketsphinx-0.8-win32\bin\Release\p
ocketsphinx_continuous.exe COMPILED ON: Dec 13 2012, AT: 17:37:32

Allocating 32 buffers of 2500 samples each
READY....

Затем я говорю, что текст и pocketsphinx_continuous пытаются распознать, но я вижу пустой вывод

Listening...
Stopped listening, please wait...
INFO: cmn_prior.c(121): cmn_prior_update: from < 56.00 -3.00  1.00  0.00  0.00
0.00  0.00  0.00  0.00  0.00  0.00  0.00  0.00 >
INFO: cmn_prior.c(139): cmn_prior_update: to   < 44.82 -2.76 -3.93 -1.62 -0.65 -
0.61  1.56  0.45 -0.66 -0.44  0.32 -0.32  0.06 >
INFO: ngram_search_fwdtree.c(1549):      593 words recognized (8/fr)
INFO: ngram_search_fwdtree.c(1551):     1818 senones evaluated (25/fr)
INFO: ngram_search_fwdtree.c(1553):      720 channels searched (10/fr), 0 1st, 7
20 last
INFO: ngram_search_fwdtree.c(1557):      720 words for which last channels evalu
ated (10/fr)
INFO: ngram_search_fwdtree.c(1560):        0 candidate words for entering last p
hone (0/fr)
INFO: ngram_search_fwdtree.c(1562): fwdtree 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdtree.c(1565): fwdtree 1.59 wall 2.208 xRT
INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(937):       77 words recognized (1/fr)
INFO: ngram_search_fwdflat.c(939):      213 senones evaluated (3/fr)
INFO: ngram_search_fwdflat.c(941):      145 channels searched (2/fr)
INFO: ngram_search_fwdflat.c(943):      145 words searched (2/fr)
INFO: ngram_search_fwdflat.c(945):       58 word transitions (0/fr)
INFO: ngram_search_fwdflat.c(948): fwdflat 0.02 CPU 0.022 xRT
INFO: ngram_search_fwdflat.c(951): fwdflat 0.00 wall 0.007 xRT
INFO: ngram_search.c(1214): </s> not found in last frame, using <sil>.70 instead

INFO: ngram_search.c(1266): lattice start node <s>.0 end node <sil>.55
INFO: ngram_search.c(1294): Eliminated 0 nodes before end node
INFO: ngram_search.c(1399): Lattice has 3 nodes, 2 links
INFO: ps_lattice.c(1365): Normalizer P(O) = alpha(<sil>:55:70) = -602868
INFO: ps_lattice.c(1403): Joint P(O,S) = -602868 P(S|O) = 0
INFO: ngram_search.c(888): bestpath 0.02 CPU 0.022 xRT
INFO: ngram_search.c(891): bestpath 0.00 wall 0.006 xRT
000000000:
READY....

Кто-нибудь может мне помочь с этим вопросом?

Спасибо.

0

Решение

ОШИБКА: «ngram_search_fwdtree.c», строка 336: ни одно слово из языковой модели не имеет p
произнесение в словаре

Эта ошибка из журнала должна подсказывать вам, что что-то пошло не так.

На самом деле, вы используете неправильную опцию, вы должны использовать -dict cmudict.dicне -dic cmudict.dic

1

Другие решения

Других решений пока нет …