Phone ‘y’ is mising in the acoustic model

[tornador92]

I’m using OpenEars to recognize Chinese，I down load the AcousticModelChinese.bundle and add it to the project. But when I run the example, it can’t recognize Chinese and the headed is always “”. I check the log, and found the result
INFO: dict.c(333): Reading main dictionary: /var/mobile/Containers/Data/Application/3702A265-EAD9-4F8C-86F9-7A849A46B65A/Library/Caches/FirstOpenEarsDynamicLanguageModel.dic
ERROR: “dict.c”, line 195: Line 1: Phone ‘y’ is mising in the acoustic model; word ‘一’ ignored
ERROR: “dict.c”, line 195: Line 2: Phone ‘es’ is mising in the acoustic model; word ‘二’ ignored
INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(336): 0 words read

But I don’t know the reason, please help me. Thank you!

[Halle Winkler]

Welcome,

Please check out the post Please read before you post – how to troubleshoot and provide logging info here so you can see how to turn on and share the logging that provides troubleshooting information for this kind of issue.

[tornador92]

Hi, Halle。 I have checked the project and find the OELogging and verbosePocketSphinx is already uncommented. I initial the array like “NSArray *firstLanguageArray = @[@”一”,@”二”];”,Just two Chinese word. I paste all the log information below, hoping it will help.

I’m using the latest version of openears. The device tested is iPhone 7 Plus running iOS 11.

If you need any other additional information, please contact with me. I really appreciate your help.Thank you.

2017-12-24 08:17:23.768921+0800 OpenEarsSampleApp[7234:1379398] +[CATransaction synchronize] called within transaction
2017-12-24 08:17:23.827629+0800 OpenEarsSampleApp[7234:1379398] [MC] Lazy loading NSBundle MobileCoreServices.framework
2017-12-24 08:17:23.828731+0800 OpenEarsSampleApp[7234:1379398] [MC] Loaded MobileCoreServices.framework
2017-12-24 08:17:23.841518+0800 OpenEarsSampleApp[7234:1379398] [MC] System group container for systemgroup.com.apple.configurationprofiles path is /private/var/containers/Shared/SystemGroup/systemgroup.com.apple.configurationprofiles
2017-12-24 08:17:23.852897+0800 OpenEarsSampleApp[7234:1379398] Starting OpenEars logging for OpenEars version 2.506 on 64-bit device (or build): iPhone running iOS version: 11.000000
2017-12-24 08:17:23.853021+0800 OpenEarsSampleApp[7234:1379398] Creating shared instance of OEPocketsphinxController
2017-12-24 08:17:23.881004+0800 OpenEarsSampleApp[7234:1379398] Starting dynamic language model generation

INFO: ngram_model_arpa_legacy.c(504): ngrams 1=4, 2=4, 3=2
INFO: ngram_model_arpa_legacy.c(136): Reading unigrams
INFO: ngram_model_arpa_legacy.c(543): 4 = #unigrams created
INFO: ngram_model_arpa_legacy.c(196): Reading bigrams
INFO: ngram_model_arpa_legacy.c(561): 4 = #bigrams created
INFO: ngram_model_arpa_legacy.c(562): 3 = #prob2 entries
INFO: ngram_model_arpa_legacy.c(570): 2 = #bo_wt2 entries
INFO: ngram_model_arpa_legacy.c(293): Reading trigrams
INFO: ngram_model_arpa_legacy.c(583): 2 = #trigrams created
INFO: ngram_model_arpa_legacy.c(584): 2 = #prob3 entries
INFO: ngram_model_dmp_legacy.c(521): Building DMP model…
INFO: ngram_model_dmp_legacy.c(551): 4 = #unigrams created
INFO: ngram_model_dmp_legacy.c(652): 4 = #bigrams created
INFO: ngram_model_dmp_legacy.c(653): 3 = #prob2 entries
INFO: ngram_model_dmp_legacy.c(660): 2 = #bo_wt2 entries
INFO: ngram_model_dmp_legacy.c(664): 2 = #trigrams created
INFO: ngram_model_dmp_legacy.c(665): 2 = #prob3 entries
2017-12-24 08:17:23.911101+0800 OpenEarsSampleApp[7234:1379398] Done creating language model with CMUCLMTK in 0.029976 seconds.
2017-12-24 08:17:23.911197+0800 OpenEarsSampleApp[7234:1379398] Since there is no cached version, loading the language model lookup list for the acoustic model called AcousticModelChinese
2017-12-24 08:17:23.929751+0800 OpenEarsSampleApp[7234:1379398] Since there is no cached version, loading the g2p model for the acoustic model called AcousticModelChinese
2017-12-24 08:17:23.956911+0800 OpenEarsSampleApp[7234:1379398] I’m done running performDictionaryLookup and it took 0.027216 seconds
2017-12-24 08:17:23.961191+0800 OpenEarsSampleApp[7234:1379398] I’m done running dynamic language model generation and it took 0.102968 seconds
2017-12-24 08:17:23.965968+0800 OpenEarsSampleApp[7234:1379398] Starting dynamic language model generation

INFO: ngram_model_arpa_legacy.c(504): ngrams 1=12, 2=19, 3=10
INFO: ngram_model_arpa_legacy.c(136): Reading unigrams
INFO: ngram_model_arpa_legacy.c(543): 12 = #unigrams created
INFO: ngram_model_arpa_legacy.c(196): Reading bigrams
INFO: ngram_model_arpa_legacy.c(561): 19 = #bigrams created
INFO: ngram_model_arpa_legacy.c(562): 3 = #prob2 entries
INFO: ngram_model_arpa_legacy.c(570): 3 = #bo_wt2 entries
INFO: ngram_model_arpa_legacy.c(293): Reading trigrams
INFO: ngram_model_arpa_legacy.c(583): 10 = #trigrams created
INFO: ngram_model_arpa_legacy.c(584): 2 = #prob3 entries
INFO: ngram_model_dmp_legacy.c(521): Building DMP model…
INFO: ngram_model_dmp_legacy.c(551): 12 = #unigrams created
INFO: ngram_model_dmp_legacy.c(652): 19 = #bigrams created
INFO: ngram_model_dmp_legacy.c(653): 3 = #prob2 entries
INFO: ngram_model_dmp_legacy.c(660): 3 = #bo_wt2 entries
INFO: ngram_model_dmp_legacy.c(664): 10 = #trigrams created
INFO: ngram_model_dmp_legacy.c(665): 2 = #prob3 entries
2017-12-24 08:17:24.052477+0800 OpenEarsSampleApp[7234:1379398] Done creating language model with CMUCLMTK in 0.086476 seconds.
2017-12-24 08:17:24.052575+0800 OpenEarsSampleApp[7234:1379398] Since there is no cached version, loading the language model lookup list for the acoustic model called AcousticModelEnglish
2017-12-24 08:17:24.082196+0800 OpenEarsSampleApp[7234:1379398] The word Quidnunc was not found in the dictionary of the acoustic model /var/containers/Bundle/Application/F1566941-8B48-42F6-8526-ED33788641F4/OpenEarsSampleApp.app/AcousticModelEnglish.bundle. Now using the fallback method to look it up. If this is happening more frequently than you would expect, likely causes can be that you are entering words in another language from the one you are recognizing, or that there are symbols (including numbers) that need to be spelled out or cleaned up, or you are using your own acoustic model and there is an issue with either its phonetic dictionary or it lacks a g2p file. Please get in touch at the forums for assistance with the last two possible issues.
2017-12-24 08:17:24.082328+0800 OpenEarsSampleApp[7234:1379398] Using convertGraphemes for the word or phrase quidnunc which doesn’t appear in the dictionary
2017-12-24 08:17:24.087586+0800 OpenEarsSampleApp[7234:1379398] Elapsed time to generate unknown word phonemes in English is 0.005311
2017-12-24 08:17:24.087668+0800 OpenEarsSampleApp[7234:1379398] the graphemes “K W IH D N AH NG K” were created for the word Quidnunc using the fallback method.
2017-12-24 08:17:24.095053+0800 OpenEarsSampleApp[7234:1379398] I’m done running performDictionaryLookup and it took 0.034667 seconds
2017-12-24 08:17:24.099399+0800 OpenEarsSampleApp[7234:1379398] I’m done running dynamic language model generation and it took 0.137961 seconds
2017-12-24 08:17:24.099690+0800 OpenEarsSampleApp[7234:1379398]

Welcome to the OpenEars sample project. This project understands the words:
(
“\U4e00”,
“\U4e8c”
),
and if you say “change model” (assuming you haven’t altered that trigger phrase in this sample app) it will switch to its dynamically-generated model which understands the words:
(
Sunday,
Monday,
Tuesday,
Wednesday,
Thursday,
Friday,
Saturday,
Quidnunc,
“change model”
)
2017-12-24 08:17:24.099996+0800 OpenEarsSampleApp[7234:1379398] Attempting to start listening session from startListeningWithLanguageModelAtPath:
2017-12-24 08:17:24.101589+0800 OpenEarsSampleApp[7234:1379398] User gave mic permission for this app.
2017-12-24 08:17:24.101676+0800 OpenEarsSampleApp[7234:1379398] setSecondsOfSilence wasn’t set, using default of 0.700000.
2017-12-24 08:17:24.102027+0800 OpenEarsSampleApp[7234:1379442] Starting listening.
2017-12-24 08:17:24.102128+0800 OpenEarsSampleApp[7234:1379442] About to set up audio session
2017-12-24 08:17:24.195082+0800 OpenEarsSampleApp[7234:1379451] Audio route has changed for the following reason:
2017-12-24 08:17:24.200810+0800 OpenEarsSampleApp[7234:1379442] Creating audio session with default settings.
2017-12-24 08:17:24.200841+0800 OpenEarsSampleApp[7234:1379442] Done setting audio session category.
2017-12-24 08:17:24.200874+0800 OpenEarsSampleApp[7234:1379451] There was a category change. The new category is AVAudioSessionCategoryPlayAndRecord
2017-12-24 08:17:24.204098+0800 OpenEarsSampleApp[7234:1379451] This is not a case in which OpenEars notifies of a route change. At the close of this method, the new audio route will be <Input route or routes: “MicrophoneBuiltIn”. Output route or routes: “Speaker”>. The previous route before changing to this route was “<AVAudioSessionRouteDescription: 0x1c421b920,
inputs = (
“<AVAudioSessionPortDescription: 0x1c421b960, type = MicrophoneBuiltIn; name = iPhone \U9ea6\U514b\U98ce; UID = Built-In Microphone; selectedDataSource = \U524d>2017-12-24 08:17:24.214392+0800 OpenEarsSampleApp[7234:1379442] Done setting preferred sample rate to 16000.000000 – now the real sample rate is 48000.000000
2017-12-24 08:17:24.224538+0800 OpenEarsSampleApp[7234:1379442] number of channels is already the preferred number of 1 so not setting it.
”
);
outputs = (
“<AVAudioSessionPortDescription: 0x1c421b7e0, type = Speaker; name = \U626c\U58f0\U5668; UID = Speaker; selectedDataSource = (null)>”
)>”.
2017-12-24 08:17:24.225081+0800 OpenEarsSampleApp[7234:1379442] Done setting session’s preferred I/O buffer duration to 0.128000 – now the actual buffer duration is 0.085333
2017-12-24 08:17:24.225101+0800 OpenEarsSampleApp[7234:1379442] Done setting up audio session
2017-12-24 08:17:24.225241+0800 OpenEarsSampleApp[7234:1379442] About to set up audio IO unit in a session with a sample rate of 48000.000000, a channel number of 1 and a buffer duration of 0.085333.
2017-12-24 08:17:24.245575+0800 OpenEarsSampleApp[7234:1379451] Audio route has changed for the following reason:
2017-12-24 08:17:24.249602+0800 OpenEarsSampleApp[7234:1379451] There was a category change. The new category is AVAudioSessionCategoryPlayAndRecord
2017-12-24 08:17:24.250840+0800 OpenEarsSampleApp[7234:1379451] This is not a case in which OpenEars notifies of a route change. At the close of this method, the new audio route will be <Input route or routes: “MicrophoneBuiltIn”. Output route or routes: “Speaker”>. The previous route before changing to this route was “<AVAudioSessionRouteDescription: 0x1c0414240,
inputs = (
“<AVAudioSessionPortDescription: 0x1c0414160, type = MicrophoneBuiltIn; name = iPhone \U9ea6\U514b\U98ce; UID = Built-In Microphone; selectedDataSource = \U4e0b>”
);
outputs = (
“<AVAudioSessionPortDescription: 0x1c0413e10, type = Receiver; name = \U63a5\U6536\U5668; UID = Built-In Receiver; selectedDataSource = (null)>”
)>”.
2017-12-24 08:17:24.251985+0800 OpenEarsSampleApp[7234:1379442] Done setting up audio unit
2017-12-24 08:17:24.252039+0800 OpenEarsSampleApp[7234:1379442] About to start audio IO unit
2017-12-24 08:17:24.395355+0800 OpenEarsSampleApp[7234:1379442] Done starting audio unit
INFO: pocketsphinx.c(145): Parsed model-specific feature parameters from /var/containers/Bundle/Application/F1566941-8B48-42F6-8526-ED33788641F4/OpenEarsSampleApp.app/AcousticModelEnglish.bundle/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
-compallsen no no
-debug 0
-dict /var/mobile/Containers/Data/Application/11ACEB61-27B4-4E6A-8E0A-9F5F942D2048/Library/Caches/FirstOpenEarsDynamicLanguageModel.dic
-dictcase no no
-dither no no
-doublebw no no
-ds 1 1
-fdict /var/containers/Bundle/Application/F1566941-8B48-42F6-8526-ED33788641F4/OpenEarsSampleApp.app/AcousticModelEnglish.bundle/noisedict
-feat 1s_c_d_dd 1s_c_d_dd
-featparams /var/containers/Bundle/Application/F1566941-8B48-42F6-8526-ED33788641F4/OpenEarsSampleApp.app/AcousticModelEnglish.bundle/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 /var/containers/Bundle/Application/F1566941-8B48-42F6-8526-ED33788641F4/OpenEarsSampleApp.app/AcousticModelEnglish.bundle
-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 /var/mobile/Containers/Data/Application/11ACEB61-27B4-4E6A-8E0A-9F5F942D2048/Library/Caches/FirstOpenEarsDynamicLanguageModel.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 /var/containers/Bundle/Application/F1566941-8B48-42F6-8526-ED33788641F4/OpenEarsSampleApp.app/AcousticModelEnglish.bundle/mdef
-mean /var/containers/Bundle/Application/F1566941-8B48-42F6-8526-ED33788641F4/OpenEarsSampleApp.app/AcousticModelEnglish.bundle/means
-mfclogdir
-min_endfr 0 0
-mixw
-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 /var/containers/Bundle/Application/F1566941-8B48-42F6-8526-ED33788641F4/OpenEarsSampleApp.app/AcousticModelEnglish.bundle/sendump
-senlogdir
-senmgau
-silprob 0.005 5.000000e-03
-smoothspec no no
-svspec 0-12/13-25/26-38
-tmat /var/containers/Bundle/Application/F1566941-8B48-42F6-8526-ED33788641F4/OpenEarsSampleApp.app/AcousticModelEnglish.bundle/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 69
-vad_prespeech 20 10
-vad_startspeech 10 10
-vad_threshold 2.0 2.300000e+00
-var /var/containers/Bundle/Application/F1566941-8B48-42F6-8526-ED33788641F4/OpenEarsSampleApp.app/AcousticModelEnglish.bundle/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: acmod.c(164): Using subvector specification 0-12/13-25/26-38
INFO: mdef.c(518): Reading model definition: /var/containers/Bundle/Application/F1566941-8B48-42F6-8526-ED33788641F4/OpenEarsSampleApp.app/AcousticModelEnglish.bundle/mdef
INFO: mdef.c(531): Found byte-order mark BMDF, assuming this is a binary mdef file
INFO: bin_mdef.c(336): Reading binary model definition: /var/containers/Bundle/Application/F1566941-8B48-42F6-8526-ED33788641F4/OpenEarsSampleApp.app/AcousticModelEnglish.bundle/mdef
INFO: bin_mdef.c(516): 46 CI-phone, 168344 CD-phone, 3 emitstate/phone, 138 CI-sen, 6138 Sen, 32881 Sen-Seq
INFO: tmat.c(206): Reading HMM transition probability matrices: /var/containers/Bundle/Application/F1566941-8B48-42F6-8526-ED33788641F4/OpenEarsSampleApp.app/AcousticModelEnglish.bundle/transition_matrices
INFO: acmod.c(117): Attempting to use PTM computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /var/containers/Bundle/Application/F1566941-8B48-42F6-8526-ED33788641F4/OpenEarsSampleApp.app/AcousticModelEnglish.bundle/means
INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:
INFO: ms_gauden.c(294): 512×13
INFO: ms_gauden.c(294): 512×13
INFO: ms_gauden.c(294): 512×13
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /var/containers/Bundle/Application/F1566941-8B48-42F6-8526-ED33788641F4/OpenEarsSampleApp.app/AcousticModelEnglish.bundle/variances
INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:
INFO: ms_gauden.c(294): 512×13
INFO: ms_gauden.c(294): 512×13
INFO: ms_gauden.c(294): 512×13
INFO: ms_gauden.c(354): 0 variance values floored
INFO: ptm_mgau.c(805): Number of codebooks doesn’t match number of ciphones, doesn’t look like PTM: 1 != 46
INFO: acmod.c(119): Attempting to use semi-continuous computation module
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /var/containers/Bundle/Application/F1566941-8B48-42F6-8526-ED33788641F4/OpenEarsSampleApp.app/AcousticModelEnglish.bundle/means
INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:
INFO: ms_gauden.c(294): 512×13
INFO: ms_gauden.c(294): 512×13
INFO: ms_gauden.c(294): 512×13
INFO: ms_gauden.c(198): Reading mixture gaussian parameter: /var/containers/Bundle/Application/F1566941-8B48-42F6-8526-ED33788641F4/OpenEarsSampleApp.app/AcousticModelEnglish.bundle/variances
INFO: ms_gauden.c(292): 1 codebook, 3 feature, size:
INFO: ms_gauden.c(294): 512×13
INFO: ms_gauden.c(294): 512×13
INFO: ms_gauden.c(294): 512×13
INFO: ms_gauden.c(354): 0 variance values floored
INFO: s2_semi_mgau.c(904): Loading senones from dump file /var/containers/Bundle/Application/F1566941-8B48-42F6-8526-ED33788641F4/OpenEarsSampleApp.app/AcousticModelEnglish.bundle/sendump
INFO: s2_semi_mgau.c(928): BEGIN FILE FORMAT DESCRIPTION
INFO: s2_semi_mgau.c(991): Rows: 512, Columns: 6138
INFO: s2_semi_mgau.c(1023): Using memory-mapped I/O for senones
INFO: s2_semi_mgau.c(1294): Maximum top-N: 4 Top-N beams: 0 0 0
INFO: phone_loop_search.c(114): State beam -225 Phone exit beam -225 Insertion penalty 0
INFO: dict.c(320): Allocating 4107 * 32 bytes (128 KiB) for word entries
INFO: dict.c(333): Reading main dictionary: /var/mobile/Containers/Data/Application/11ACEB61-27B4-4E6A-8E0A-9F5F942D2048/Library/Caches/FirstOpenEarsDynamicLanguageModel.dic
ERROR: “dict.c”, line 195: Line 1: Phone ‘y’ is mising in the acoustic model; word ‘一’ ignored
ERROR: “dict.c”, line 195: Line 2: Phone ‘es’ is mising in the acoustic model; word ‘二’ ignored
INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(336): 0 words read
INFO: dict.c(358): Reading filler dictionary: /var/containers/Bundle/Application/F1566941-8B48-42F6-8526-ED33788641F4/OpenEarsSampleApp.app/AcousticModelEnglish.bundle/noisedict
INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones
INFO: dict.c(361): 9 words read
INFO: dict2pid.c(396): Building PID tables for dictionary
INFO: dict2pid.c(406): Allocating 46^3 * 2 bytes (190 KiB) for word-initial triphones
INFO: dict2pid.c(132): Allocated 51152 bytes (49 KiB) for word-final triphones
INFO: dict2pid.c(196): Allocated 51152 bytes (49 KiB) for single-phone word triphones
INFO: ngram_model_trie.c(424): Trying to read LM in bin format
INFO: ngram_model_trie.c(457): Header doesn’t match
INFO: ngram_model_trie.c(180): Trying to read LM in arpa format
INFO: ngram_model_trie.c(71): No \data\ mark in LM file
INFO: ngram_model_trie.c(537): Trying to read LM in DMP format
INFO: ngram_model_trie.c(632): ngrams 1=4, 2=4, 3=2
INFO: lm_trie.c(317): Training quantizer
INFO: lm_trie.c(323): Building LM trie
INFO: ngram_search_fwdtree.c(99): 0 unique initial diphones
INFO: ngram_search_fwdtree.c(148): 0 root, 0 non-root channels, 10 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, 10 single-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 pronunciation in the dictionary
INFO: ngram_search_fwdtree.c(339): after: 0 root, 0 non-root channels, 9 single-phone words
INFO: ngram_search_fwdflat.c(157): fwdflat: min_ef_width = 4, max_sf_win = 25
2017-12-24 08:17:24.450054+0800 OpenEarsSampleApp[7234:1379442] Restoring SmartCMN value of 25.487793
2017-12-24 08:17:24.450763+0800 OpenEarsSampleApp[7234:1379442] Listening.
2017-12-24 08:17:24.451344+0800 OpenEarsSampleApp[7234:1379442] Project has these words or phrases in its dictionary:
一
二
2017-12-24 08:17:24.451386+0800 OpenEarsSampleApp[7234:1379442] Recognition loop has started
2017-12-24 08:17:24.474426+0800 OpenEarsSampleApp[7234:1379398] Successfully started listening session from startListeningWithLanguageModelAtPath:
2017-12-24 08:17:24.490773+0800 OpenEarsSampleApp[7234:1379398] Local callback: Pocketsphinx is now listening.
2017-12-24 08:17:24.491554+0800 OpenEarsSampleApp[7234:1379398] Local callback: Pocketsphinx started.
2017-12-24 08:17:24.494784+0800 OpenEarsSampleApp[7234:1379398] refreshPreferences: HangTracerEnabled: 0
2017-12-24 08:17:24.494816+0800 OpenEarsSampleApp[7234:1379398] refreshPreferences: HangTracerDuration: 500
2017-12-24 08:17:24.494833+0800 OpenEarsSampleApp[7234:1379398] refreshPreferences: ActivationLoggingEnabled: 0 ActivationLoggingTaskedOffByDA:0
2017-12-24 08:17:24.663027+0800 OpenEarsSampleApp[7234:1379440] Speech detected…
2017-12-24 08:17:24.663175+0800 OpenEarsSampleApp[7234:1379398] Local callback: Pocketsphinx has detected speech.
2017-12-24 08:17:25.821560+0800 OpenEarsSampleApp[7234:1379442] End of speech detected…
2017-12-24 08:17:25.825526+0800 OpenEarsSampleApp[7234:1379398] Local callback: Pocketsphinx has detected a second of silence, concluding an utterance.
INFO: cmn_prior.c(131): cmn_prior_update: from < 25.49 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 < 29.68 -10.93 -5.43 4.85 1.33 4.65 2.33 2.13 1.71 0.23 1.02 0.91 1.04 >
INFO: ngram_search_fwdtree.c(1553): 992 words recognized (8/fr)
INFO: ngram_search_fwdtree.c(1555): 2550 senones evaluated (20/fr)
INFO: ngram_search_fwdtree.c(1559): 1017 channels searched (8/fr), 0 1st, 1017 last
INFO: ngram_search_fwdtree.c(1562): 1017 words for which last channels evaluated (8/fr)
INFO: ngram_search_fwdtree.c(1564): 0 candidate words for entering last phone (0/fr)
INFO: ngram_search_fwdtree.c(1567): fwdtree 0.08 CPU 0.064 xRT
INFO: ngram_search_fwdtree.c(1570): fwdtree 1.19 wall 0.947 xRT
INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(948): 1080 words recognized (9/fr)
INFO: ngram_search_fwdflat.c(950): 2571 senones evaluated (20/fr)
INFO: ngram_search_fwdflat.c(952): 1101 channels searched (8/fr)
INFO: ngram_search_fwdflat.c(954): 1101 words searched (8/fr)
INFO: ngram_search_fwdflat.c(957): 76 word transitions (0/fr)
INFO: ngram_search_fwdflat.c(960): fwdflat 0.01 CPU 0.011 xRT
INFO: ngram_search_fwdflat.c(963): fwdflat 0.02 wall 0.012 xRT
INFO: ngram_search.c(1290): lattice start node <s>.0 end node </s>.82
INFO: ngram_search.c(1320): Eliminated 5 nodes before end node
INFO: ngram_search.c(1445): Lattice has 598 nodes, 3351 links
INFO: ps_lattice.c(1380): Bestpath score: -52028
INFO: ps_lattice.c(1384): Normalizer P(O) = alpha(</s>:82:124) = -3373434
INFO: ps_lattice.c(1441): Joint P(O,S) = -3402896 P(S|O) = -29462
INFO: ngram_search.c(901): bestpath 0.01 CPU 0.006 xRT
INFO: ngram_search.c(904): bestpath 0.01 wall 0.006 xRT
2017-12-24 08:17:25.866333+0800 OpenEarsSampleApp[7234:1379442] Pocketsphinx heard “” with a score of (-29462) and an utterance ID of 0.
2017-12-24 08:17:25.866425+0800 OpenEarsSampleApp[7234:1379442] Hypothesis was null so we aren’t returning it. If you want null hypotheses to also be returned, set OEPocketsphinxController’s property returnNullHypotheses to TRUE before starting OEPocketsphinxController.
2017-12-24 08:17:30.559058+0800 OpenEarsSampleApp[7234:1379442] Speech detected…
2017-12-24 08:17:30.559357+0800 OpenEarsSampleApp[7234:1379398] Local callback: Pocketsphinx has detected speech.
2017-12-24 08:17:33.495153+0800 OpenEarsSampleApp[7234:1379442] End of speech detected…
2017-12-24 08:17:33.495757+0800 OpenEarsSampleApp[7234:1379398] Local callback: Pocketsphinx has detected a second of silence, concluding an utterance.
INFO: cmn_prior.c(131): cmn_prior_update: from < 29.68 -10.93 -5.43 4.85 1.33 4.65 2.33 2.13 1.71 0.23 1.02 0.91 1.04 >
INFO: cmn_prior.c(149): cmn_prior_update: to < 34.43 -13.25 -7.97 2.60 -0.04 3.63 -0.91 0.19 1.41 -0.17 0.79 1.72 -0.31 >
INFO: ngram_search_fwdtree.c(1553): 2404 words recognized (8/fr)
INFO: ngram_search_fwdtree.c(1555): 6309 senones evaluated (21/fr)
INFO: ngram_search_fwdtree.c(1559): 2429 channels searched (7/fr), 0 1st, 2429 last
INFO: ngram_search_fwdtree.c(1562): 2429 words for which last channels evaluated (7/fr)
INFO: ngram_search_fwdtree.c(1564): 0 candidate words for entering last phone (0/fr)
INFO: ngram_search_fwdtree.c(1567): fwdtree 0.48 CPU 0.157 xRT
INFO: ngram_search_fwdtree.c(1570): fwdtree 7.64 wall 2.512 xRT
INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 1 words
INFO: ngram_search_fwdflat.c(948): 2681 words recognized (9/fr)
INFO: ngram_search_fwdflat.c(950): 6309 senones evaluated (21/fr)
INFO: ngram_search_fwdflat.c(952): 2703 channels searched (8/fr)
INFO: ngram_search_fwdflat.c(954): 2703 words searched (8/fr)
INFO: ngram_search_fwdflat.c(957): 26 word transitions (0/fr)
INFO: ngram_search_fwdflat.c(960): fwdflat 0.04 CPU 0.012 xRT
INFO: ngram_search_fwdflat.c(963): fwdflat 0.04 wall 0.012 xRT
INFO: ngram_search.c(1290): lattice start node <s>.0 end node </s>.300
INFO: ngram_search.c(1320): Eliminated 5 nodes before end node
INFO: ngram_search.c(1445): Lattice has 1628 nodes, 12764 links
INFO: ps_lattice.c(1380): Bestpath score: -78391
INFO: ps_lattice.c(1384): Normalizer P(O) = alpha(</s>:300:302) = -4448890
INFO: ps_lattice.c(1441): Joint P(O,S) = -4507332 P(S|O) = -58442
INFO: ngram_search.c(901): bestpath 0.03 CPU 0.010 xRT
INFO: ngram_search.c(904): bestpath 0.03 wall 0.010 xRT
2017-12-24 08:17:33.573265+0800 OpenEarsSampleApp[7234:1379442] Pocketsphinx heard “” with a score of (-58442) and an utterance ID of 1.
2017-12-24 08:17:33.573412+0800 OpenEarsSampleApp[7234:1379442] Hypothesis was null so we aren’t returning it. If you want null hypotheses to also be returned, set OEPocketsphinxController’s property returnNullHypotheses to TRUE before starting OEPocketsphinxController.
2017-12-24 08:17:34.404991+0800 OpenEarsSampleApp[7234:1379441] Speech detected…
2017-12-24 08:17:34.405680+0800 OpenEarsSampleApp[7234:1379398] Local callback: Pocketsphinx has detected speech.
2017-12-24 08:17:36.715539+0800 OpenEarsSampleApp[7234:1379442] End of speech detected…
2017-12-24 08:17:36.716253+0800 OpenEarsSampleApp[7234:1379398] Local callback: Pocketsphinx has detected a second of silence, concluding an utterance.
INFO: cmn_prior.c(131): cmn_prior_update: from < 34.43 -13.25 -7.97 2.60 -0.04 3.63 -0.91 0.19 1.41 -0.17 0.79 1.72 -0.31 >
INFO: cmn_prior.c(149): cmn_prior_update: to < 33.41 -11.07 -4.17 6.47 0.75 4.03 -1.47 1.71 1.39 -0.13 -0.10 1.26 -0.37 >
INFO: ngram_search_fwdtree.c(1553): 1993 words recognized (8/fr)
INFO: ngram_search_fwdtree.c(1555): 5049 senones evaluated (21/fr)
INFO: ngram_search_fwdtree.c(1559): 2012 channels searched (8/fr), 0 1st, 2012 last
INFO: ngram_search_fwdtree.c(1562): 2012 words for which last channels evaluated (8/fr)
INFO: ngram_search_fwdtree.c(1564): 0 candidate words for entering last phone (0/fr)
INFO: ngram_search_fwdtree.c(1567): fwdtree 0.27 CPU 0.111 xRT
INFO: ngram_search_fwdtree.c(1570): fwdtree 3.16 wall 1.293 xRT
INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(948): 2145 words recognized (9/fr)
INFO: ngram_search_fwdflat.c(950): 5049 senones evaluated (21/fr)
INFO: ngram_search_fwdflat.c(952): 2163 channels searched (8/fr)
INFO: ngram_search_fwdflat.c(954): 2163 words searched (8/fr)
INFO: ngram_search_fwdflat.c(957): 76 word transitions (0/fr)
INFO: ngram_search_fwdflat.c(960): fwdflat 0.03 CPU 0.011 xRT
INFO: ngram_search_fwdflat.c(963): fwdflat 0.03 wall 0.013 xRT
INFO: ngram_search.c(1290): lattice start node <s>.0 end node </s>.207
INFO: ngram_search.c(1320): Eliminated 3 nodes before end node
INFO: ngram_search.c(1445): Lattice has 779 nodes, 4454 links
INFO: ps_lattice.c(1380): Bestpath score: -72179
INFO: ps_lattice.c(1384): Normalizer P(O) = alpha(</s>:207:242) = -4239412
INFO: ps_lattice.c(1441): Joint P(O,S) = -4377232 P(S|O) = -137820
INFO: ngram_search.c(901): bestpath 0.01 CPU 0.003 xRT
INFO: ngram_search.c(904): bestpath 0.01 wall 0.004 xRT
2017-12-24 08:17:36.771777+0800 OpenEarsSampleApp[7234:1379442] Pocketsphinx heard “” with a score of (-137820) and an utterance ID of 2.
2017-12-24 08:17:36.771911+0800 OpenEarsSampleApp[7234:1379442] Hypothesis was null so we aren’t returning it. If you want null hypotheses to also be returned, set OEPocketsphinxController’s property returnNullHypotheses to TRUE before starting OEPocketsphinxController.
2017-12-24 08:17:37.482080+0800 OpenEarsSampleApp[7234:1379442] Speech detected…
2017-12-24 08:17:37.482444+0800 OpenEarsSampleApp[7234:1379398] Local callback: Pocketsphinx has detected speech.
2017-12-24 08:17:38.205290+0800 OpenEarsSampleApp[7234:1379440] End of speech detected…
INFO: cmn_prior.c(131): cmn_prior_update: from < 2017-12-24 08:17:38.205561+0800 OpenEarsSampleApp[7234:1379398] Local callback: Pocketsphinx has detected a second of silence, concluding an utterance.
33.41 -11.07 -4.17 6.47 0.75 4.03 -1.47 1.71 1.39 -0.13 -0.10 1.26 -0.37 >
INFO: cmn_prior.c(149): cmn_prior_update: to < 32.56 -11.29 -4.30 6.68 0.68 4.52 -1.32 1.82 1.76 -0.13 0.31 0.86 0.03 >
INFO: ngram_search_fwdtree.c(1553): 656 words recognized (8/fr)
INFO: ngram_search_fwdtree.c(1555): 1584 senones evaluated (20/fr)
INFO: ngram_search_fwdtree.c(1559): 678 channels searched (8/fr), 0 1st, 678 last
INFO: ngram_search_fwdtree.c(1562): 678 words for which last channels evaluated (8/fr)
INFO: ngram_search_fwdtree.c(1564): 0 candidate words for entering last phone (0/fr)
INFO: ngram_search_fwdtree.c(1567): fwdtree 0.12 CPU 0.149 xRT
INFO: ngram_search_fwdtree.c(1570): fwdtree 1.44 wall 1.823 xRT
INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(948): 656 words recognized (8/fr)
INFO: ngram_search_fwdflat.c(950): 1584 senones evaluated (20/fr)
INFO: ngram_search_fwdflat.c(952): 678 channels searched (8/fr)
INFO: ngram_search_fwdflat.c(954): 678 words searched (8/fr)
INFO: ngram_search_fwdflat.c(957): 75 word transitions (0/fr)
INFO: ngram_search_fwdflat.c(960): fwdflat 0.01 CPU 0.011 xRT
INFO: ngram_search_fwdflat.c(963): fwdflat 0.01 wall 0.016 xRT
INFO: ngram_search.c(1290): lattice start node <s>.0 end node </s>.23
INFO: ngram_search.c(1320): Eliminated 3 nodes before end node
INFO: ngram_search.c(1445): Lattice has 320 nodes, 361 links
INFO: ps_lattice.c(1380): Bestpath score: -45337
INFO: ps_lattice.c(1384): Normalizer P(O) = alpha(</s>:23:77) = -3089019
INFO: ps_lattice.c(1441): Joint P(O,S) = -3107523 P(S|O) = -18504
INFO: ngram_search.c(901): bestpath 0.00 CPU 0.002 xRT
INFO: ngram_search.c(904): bestpath 0.00 wall 0.002 xRT
2017-12-24 08:17:38.227900+0800 OpenEarsSampleApp[7234:1379440] Pocketsphinx heard “” with a score of (-18504) and an utterance ID of 3.
2017-12-24 08:17:38.228020+0800 OpenEarsSampleApp[7234:1379440] Hypothesis was null so we aren’t returning it. If you want null hypotheses to also be returned, set OEPocketsphinxController’s property returnNullHypotheses to TRUE before starting OEPocketsphinxController.
2017-12-24 08:17:41.578775+0800 OpenEarsSampleApp[7234:1379440] Speech detected…
2017-12-24 08:17:41.579358+0800 OpenEarsSampleApp[7234:1379398] Local callback: Pocketsphinx has detected speech.
INFO: cmn_prior.c(99): cmn_prior_update: from < 32.56 -11.29 -4.30 6.68 0.68 4.52 -1.32 1.82 1.76 -0.13 0.31 0.86 0.03 >
INFO: cmn_prior.c(116): cmn_prior_update: to < 32.41 -11.55 -4.68 6.60 0.73 5.08 -1.41 2.25 1.85 -0.14 0.40 1.35 0.24 >
2017-12-24 08:17:43.101381+0800 OpenEarsSampleApp[7234:1379439] End of speech detected…
2017-12-24 08:17:43.101982+0800 OpenEarsSampleApp[7234:1379398] Local callback: Pocketsphinx has detected a second of silence, concluding an utterance.
INFO: cmn_prior.c(131): cmn_prior_update: from < 32.41 -11.55 -4.68 6.60 0.73 5.08 -1.41 2.25 1.85 -0.14 0.40 1.35 0.24 >
INFO: cmn_prior.c(149): cmn_prior_update: to < 30.15 -11.80 -4.16 6.25 0.27 5.88 -0.73 3.28 2.36 0.07 1.06 1.18 0.77 >
INFO: ngram_search_fwdtree.c(1553): 1344 words recognized (8/fr)
INFO: ngram_search_fwdtree.c(1555): 3264 senones evaluated (21/fr)
INFO: ngram_search_fwdtree.c(1559): 1398 channels searched (8/fr), 0 1st, 1398 last
INFO: ngram_search_fwdtree.c(1562): 1398 words for which last channels evaluated (8/fr)
INFO: ngram_search_fwdtree.c(1564): 0 candidate words for entering last phone (0/fr)
INFO: ngram_search_fwdtree.c(1567): fwdtree 0.38 CPU 0.240 xRT
INFO: ngram_search_fwdtree.c(1570): fwdtree 4.88 wall 3.070 xRT
INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(948): 1359 words recognized (9/fr)
INFO: ngram_search_fwdflat.c(950): 3264 senones evaluated (21/fr)
INFO: ngram_search_fwdflat.c(952): 1398 channels searched (8/fr)
INFO: ngram_search_fwdflat.c(954): 1398 words searched (8/fr)
INFO: ngram_search_fwdflat.c(957): 76 word transitions (0/fr)
INFO: ngram_search_fwdflat.c(960): fwdflat 0.02 CPU 0.013 xRT
INFO: ngram_search_fwdflat.c(963): fwdflat 0.03 wall 0.017 xRT
INFO: ngram_search.c(1290): lattice start node <s>.0 end node </s>.92
INFO: ngram_search.c(1320): Eliminated 6 nodes before end node
INFO: ngram_search.c(1445): Lattice has 590 nodes, 1536 links
INFO: ps_lattice.c(1380): Bestpath score: -53946
INFO: ps_lattice.c(1384): Normalizer P(O) = alpha(</s>:92:157) = -3550968
INFO: ps_lattice.c(1441): Joint P(O,S) = -3596943 P(S|O) = -45975
INFO: ngram_search.c(901): bestpath 0.01 CPU 0.003 xRT
INFO: ngram_search.c(904): bestpath 0.00 wall 0.003 xRT
2017-12-24 08:17:43.145170+0800 OpenEarsSampleApp[7234:1379439] Pocketsphinx heard “” with a score of (-45975) and an utterance ID of 4.
2017-12-24 08:17:43.145289+0800 OpenEarsSampleApp[7234:1379439] Hypothesis was null so we aren’t returning it. If you want null hypotheses to also be returned, set OEPocketsphinxController’s property returnNullHypotheses to TRUE before starting OEPocketsphinxController.
2017-12-24 08:17:43.498446+0800 OpenEarsSampleApp[7234:1379439] Speech detected…
2017-12-24 08:17:43.499101+0800 OpenEarsSampleApp[7234:1379398] Local callback: Pocketsphinx has detected speech.
2017-12-24 08:17:44.488059+0800 OpenEarsSampleApp[7234:1379440] End of speech detected…
2017-12-24 08:17:44.489454+0800 OpenEarsSampleApp[7234:1379398] Local callback: Pocketsphinx has detected a second of silence, concluding an utterance.
INFO: cmn_prior.c(131): cmn_prior_update: from < 30.15 -11.80 -4.16 6.25 0.27 5.88 -0.73 3.28 2.36 0.07 1.06 1.18 0.77 >
INFO: cmn_prior.c(149): cmn_prior_update: to < 31.34 -11.65 -4.95 6.17 0.43 5.40 -0.57 3.25 2.18 0.12 1.00 1.08 0.70 >
INFO: ngram_search_fwdtree.c(1553): 897 words recognized (8/fr)
INFO: ngram_search_fwdtree.c(1555): 2340 senones evaluated (20/fr)
INFO: ngram_search_fwdtree.c(1559): 919 channels searched (7/fr), 0 1st, 919 last
INFO: ngram_search_fwdtree.c(1562): 919 words for which last channels evaluated (7/fr)
INFO: ngram_search_fwdtree.c(1564): 0 candidate words for entering last phone (0/fr)
INFO: ngram_search_fwdtree.c(1567): fwdtree 0.13 CPU 0.117 xRT
INFO: ngram_search_fwdtree.c(1570): fwdtree 1.36 wall 1.181 xRT
INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 2 words
INFO: ngram_search_fwdflat.c(948): 982 words recognized (9/fr)
INFO: ngram_search_fwdflat.c(950): 2340 senones evaluated (20/fr)
INFO: ngram_search_fwdflat.c(952): 1002 channels searched (8/fr)
INFO: ngram_search_fwdflat.c(954): 1002 words searched (8/fr)
INFO: ngram_search_fwdflat.c(957): 76 word transitions (0/fr)
INFO: ngram_search_fwdflat.c(960): fwdflat 0.01 CPU 0.009 xRT
INFO: ngram_search_fwdflat.c(963): fwdflat 0.02 wall 0.017 xRT
INFO: ngram_search.c(1290): lattice start node <s>.0 end node </s>.65
INFO: ngram_search.c(1320): Eliminated 4 nodes before end node
INFO: ngram_search.c(1445): Lattice has 544 nodes, 2113 links
INFO: ps_lattice.c(1380): Bestpath score: -50540
INFO: ps_lattice.c(1384): Normalizer P(O) = alpha(</s>:65:113) = -3295562
INFO: ps_lattice.c(1441): Joint P(O,S) = -3326609 P(S|O) = -31047
INFO: ngram_search.c(901): bestpath 0.01 CPU 0.009 xRT
INFO: ngram_search.c(904): bestpath 0.01 wall 0.006 xRT
2017-12-24 08:17:44.530497+0800 OpenEarsSampleApp[7234:1379440] Pocketsphinx heard “” with a score of (-31047) and an utterance ID of 5.
2017-12-24 08:17:44.530641+0800 OpenEarsSampleApp[7234:1379440] Hypothesis was null so we aren’t returning it. If you want null hypotheses to also be returned, set OEPocketsphinxController’s property returnNullHypotheses to TRUE before starting OEPocketsphinxController.

[Halle Winkler]

It looks like the problem is that you’re generating the dynamic model with the Chinese acoustic model but you’re starting speech recognition with the English one, so just review whether you have replaced the English model with the Chinese model in all your code, or if you have overlooked one place.

[Author]

Posts