CMU Sphinx / Forums / Help: Pocketsphinx_continuous cmd output does not give recognized words

Hi,

I recently trained an acoustic model for a small subset of the arabic language (1300 words approximately).

The training passed in CONTINUOUS and PTM modes and I am now manually testing with the pocketsphinx_continuous command to check if the results are OK.

The problem is that I first tried with the CONTINUOUS model and I have no recognized words from the output. Only infos that I cannot clearly understand.

I searched for same problems in the forum and it was mostly due to a wrong audio file format but I checked my audio file and it is the right format (16 khz, 16 bit signed integer PCM).

Could you please have a look and tell me if there is a problem?

Thanks a lot for your help,

Here is the command I ran:

pocketsphinx_continuous -hmm arabic.cd_cont_3000/ -lm arabic.lm.DMP -dict arabic.dic -infile 079013.wav -samprate 16000

Here is the result:

INFO: cmd_ln.c(697): Parsing command line:
pocketsphinx_continuous \
-hmm arabic.cd_cont_3000/ \
-lm arabic.lm.DMP \
-dict arabic.dic \
-infile 079013.wav \
-samprate 16000
Current configuration:
[NAME] [DEFLT] [VALUE]
-adcdev
-agc none none
-agcthresh 2.0 2.000000e+00
-allphone
-allphone_ci no no
-alpha 0.97 9.700000e-01
-argfile
-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 8.0
-compallsen no no
-debug 0
-dict arabic.dic
-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-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 arabic.cd_cont_3000/
-infile 079013.wav
-inmic no no
-input_endian little little
-jsgf
-keyphrase
-kws
-kws_plp 1e-1 1.000000e-01
-kws_threshold 1 1.000000e+00
-latsize 5000 5000
-lda
-ldadim 0 0
-lifter 0 0
-lm arabic.lm.DMP
-lmctl
-lmname
-logbase 1.0001 1.000100e+00
-logfn
-logspec no no
-lowerf 133.33334 1.333333e+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
-mean
-mfclogdir
-min_endfr 0 0
-mixw
-mixwfloor 0.0000001 1.000000e-07
-mllr
-mmap yes yes
-ncep 13 13
-nfft 512 512
-nfilt 40 40
-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
-time no no
-tmat
-tmatfloor 0.0001 1.000000e-04
-topn 4 4
-topn_beam 0 0
-toprule
-transform legacy legacy
-unit_area yes yes
-upperf 6855.4976 6.855498e+03
-uw 1.0 1.000000e+00
-vad_postspeech 50 50
-vad_prespeech 10 10
-vad_threshold 2.0 2.000000e+00
-var
-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: cmd_ln.c(697): Parsing command line:
\
-lowerf 130 \
-upperf 6800 \
-nfilt 25 \
-transform dct \
-lifter 22 \
-feat 1s_c_d_dd \
-agc none \
-cmn current \
-varnorm no
Current configuration:
[NAME] [DEFLT] [VALUE]
-agc none none
-agcthresh 2.0 2.000000e+00
-alpha 0.97 9.700000e-01
-ceplen 13 13
-cmn current current
-cmninit 8.0 8.0
-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 22
-logspec no no
-lowerf 133.33334 1.300000e+02
-ncep 13 13
-nfft 512 512
-nfilt 40 25
-remove_dc no no
-remove_noise yes yes
-remove_silence yes yes
-round_filters yes yes
-samprate 16000 1.600000e+04
-seed -1 -1
-smoothspec no no
-svspec
-transform legacy dct
-unit_area yes yes
-upperf 6855.4976 6.800000e+03
-vad_postspeech 50 50
-vad_prespeech 10 10
-vad_threshold 2.0 2.000000e+00
-varnorm no no
-verbose no no
-warp_params
-warp_type inverse_linear inverse_linear
-wlen 0.025625 2.562500e-02
INFO: acmod.c(252): Parsed model-specific feature parameters from arabic.cd_cont_3000//feat.params
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: arabic.cd_cont_3000//mdef
INFO: bin_mdef.c(181): Allocating 11854 * 8 bytes (92 KiB) for CD tree
INFO: tmat.c(206): Reading HMM transition probability matrices: arabic.cd_cont_3000//transition_matrices
INFO: acmod.c(124): Attempting to use PTM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: arabic.cd_cont_3000//means
INFO: ms_gauden.c(292): 3120 codebook, 1 feature, size:
INFO: ms_gauden.c(294): 8x39
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: arabic.cd_cont_3000//variances
INFO: ms_gauden.c(292): 3120 codebook, 1 feature, size:
INFO: ms_gauden.c(294): 8x39
INFO: ms_gauden.c(354): 0 variance values floored
INFO: ptm_mgau.c(801): Number of codebooks exceeds 256: 3120
INFO: acmod.c(126): Attempting to use semi-continuous computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: arabic.cd_cont_3000//means
INFO: ms_gauden.c(292): 3120 codebook, 1 feature, size:
INFO: ms_gauden.c(294): 8x39
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: arabic.cd_cont_3000//variances
INFO: ms_gauden.c(292): 3120 codebook, 1 feature, size:
INFO: ms_gauden.c(294): 8x39
INFO: ms_gauden.c(354): 0 variance values floored
INFO: acmod.c(128): Falling back to general multi-stream GMM computation
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: arabic.cd_cont_3000//means
INFO: ms_gauden.c(292): 3120 codebook, 1 feature, size:
INFO: ms_gauden.c(294): 8x39
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: arabic.cd_cont_3000//variances
INFO: ms_gauden.c(292): 3120 codebook, 1 feature, size:
INFO: ms_gauden.c(294): 8x39
INFO: ms_gauden.c(354): 0 variance values floored
INFO: ms_senone.c(149): Reading senone mixture weights: arabic.cd_cont_3000//mixture_weights
INFO: ms_senone.c(200): Truncating senone logs3(pdf) values by 10 bits
INFO: ms_senone.c(207): Not transposing mixture weights in memory
INFO: ms_senone.c(268): Read mixture weights for 3120 senones: 1 features x 8 codewords
INFO: ms_senone.c(320): Mapping senones to individual codebooks
INFO: ms_mgau.c(141): The value of topn: 4
INFO: phone_loop_search.c(115): State beam -225 Phone exit beam -225 Insertion penalty 0
INFO: dict.c(320): Allocating 5483 * 32 bytes (171 KiB) for word entries
INFO: dict.c(333): Reading main dictionary: arabic.dic
INFO: dict.c(213): Allocated 23 KiB for strings, 20 KiB for phones
INFO: dict.c(336): 1384 words read
INFO: dict.c(342): Reading filler dictionary: arabic.cd_cont_3000//noisedict
INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(345): 3 words read
INFO: dict2pid.c(396): Building PID tables for dictionary
INFO: dict2pid.c(406): Allocating 40^3 * 2 bytes (125 KiB) for word-initial triphones
INFO: dict2pid.c(132): Allocated 38720 bytes (37 KiB) for word-final triphones
INFO: dict2pid.c(196): Allocated 38720 bytes (37 KiB) for single-phone word triphones
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=1386, 2=2375, 3=2970
INFO: ngram_model_dmp.c(242): 1386 = LM.unigrams(+trailer) read
INFO: ngram_model_dmp.c(288): 2375 = LM.bigrams(+trailer) read
INFO: ngram_model_dmp.c(314): 2970 = LM.trigrams read
INFO: ngram_model_dmp.c(339): 75 = LM.prob2 entries read
INFO: ngram_model_dmp.c(359): 115 = LM.bo_wt2 entries read
INFO: ngram_model_dmp.c(379): 55 = LM.prob3 entries read
INFO: ngram_model_dmp.c(407): 5 = LM.tseg_base entries read
INFO: ngram_model_dmp.c(463): 1386 = ascii word strings read
INFO: ngram_search_fwdtree.c(99): 138 unique initial diphones
INFO: ngram_search_fwdtree.c(148): 0 root, 0 non-root channels, 4 single-phone words
INFO: ngram_search_fwdtree.c(186): Creating search tree
INFO: ngram_search_fwdtree.c(192): before: 0 root, 0 non-root channels, 4 single-phone words
INFO: ngram_search_fwdtree.c(326): after: max nonroot chan increased to 6257
INFO: ngram_search_fwdtree.c(339): after: 138 root, 6129 non-root channels, 3 single-phone words
INFO: ngram_search_fwdflat.c(157): fwdflat: min_ef_width = 4, max_sf_win = 25
INFO: continuous.c(299): pocketsphinx_continuous COMPILED ON: Jun 1 2015, AT: 15:48:38
INFO: cmn_prior.c(131): cmn_prior_update: from < 8.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 0.00 >
INFO: cmn_prior.c(149): cmn_prior_update: to < 73.73 4.09 -21.00 23.73 -18.06 -14.50 -2.88 -21.45 1.83 -14.21 5.62 -2.52 -5.64 >
INFO: ngram_search_fwdtree.c(1553): 1216 words recognized (3/fr)
INFO: ngram_search_fwdtree.c(1555): 61689 senones evaluated (142/fr)
INFO: ngram_search_fwdtree.c(1559): 31398 channels searched (72/fr), 27131 1st, 1223 last
INFO: ngram_search_fwdtree.c(1562): 1223 words for which last channels evaluated (2/fr)
INFO: ngram_search_fwdtree.c(1564): 0 candidate words for entering last phone (0/fr)
INFO: ngram_search_fwdtree.c(1567): fwdtree 0.10 CPU 0.023 xRT
INFO: ngram_search_fwdtree.c(1570): fwdtree 0.10 wall 0.023 xRT
INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(945): 1216 words recognized (3/fr)
INFO: ngram_search_fwdflat.c(947): 1296 senones evaluated (3/fr)
INFO: ngram_search_fwdflat.c(949): 1290 channels searched (2/fr)
INFO: ngram_search_fwdflat.c(951): 1290 words searched (2/fr)
INFO: ngram_search_fwdflat.c(954): 76 word transitions (0/fr)
INFO: ngram_search_fwdflat.c(957): fwdflat 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdflat.c(960): fwdflat 0.00 wall 0.001 xRT
INFO: ngram_search.c(1252): lattice start node ~~.0 end node~~ .374
INFO: ngram_search.c(1278): Eliminated 0 nodes before end node
INFO: ngram_search.c(1383): Lattice has 12 nodes, 14 links
INFO: ps_lattice.c(1380): Bestpath score: -2554
INFO: ps_lattice.c(1384): Normalizer P(O) = alpha(:374:431) = -153539
INFO: ps_lattice.c(1441): Joint P(O,S) = -166369 P(S|O) = -12830
INFO: ngram_search.c(874): bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(877): bestpath 0.00 wall 0.000 xRT
INFO: ngram_search_fwdtree.c(432): TOTAL fwdtree 0.10 CPU 0.023 xRT
INFO: ngram_search_fwdtree.c(435): TOTAL fwdtree 0.10 wall 0.023 xRT
INFO: ngram_search_fwdflat.c(176): TOTAL fwdflat 0.00 CPU 0.000 xRT
INFO: ngram_search_fwdflat.c(179): TOTAL fwdflat 0.00 wall 0.001 xRT
INFO: ngram_search.c(303): TOTAL bestpath 0.00 CPU 0.000 xRT
INFO: ngram_search.c(306): TOTAL bestpath 0.00 wall 0.000 xRT

Pocketsphinx_continuous cmd output does not give recognized words

Speech Recognition Toolkit

Forums

Help

Pocketsphinx_continuous cmd output does not give recognized words document.SUBSCRIPTION_OPTIONS = { "thing": "topic", "subscribed": false, "url": "subscribe", "icon": { "css": "fa fa-envelope-o" } };

Pocketsphinx_continuous cmd output does not give recognized words