Recognition Score is Always Zero (0)

Home Forums OpenEars Recognition Score is Always Zero (0)

Viewing 2 posts - 1 through 2 (of 2 total)

  • Author
    Posts
  • #1032429
    jrscorca
    Participant

    Hi Halle,

    I’m making a very simple app that seeks to log recognition scores using pathToTestFile (following your .wav instructions). The problem I have is that the recognition score of every hypothesis in my session is (0). I’ve tried changing the grammar to no avail. I’ve also tried using my voice instead of pathToTestFile and I still see all recognition scores as (0). Am I missing something or is this a bug?

    Here are the logs. I am using your sample grammar. I am feeding a .wav file through pathToTestFile. The .wav file features my voice speaking a phrase recognizable by your sample grammar. It is recognized with a score of (0). I know this only demonstrates one instance of a “certain” score. If you need a session with multiple scores of (0) please let me know.

    Notes : Running on iPhone X, recorded using Voice Memos on same iPhone X. Converted to .wav using the terminal commands you specify.

    2018-05-01 13:49:13.794510-0700 BatchRecognizer[18593:7082913] Starting OpenEars logging for OpenEars version 2.506 on 64-bit device (or build): iPhone running iOS version: 11.300000
    2018-05-01 13:49:13.795247-0700 BatchRecognizer[18593:7082913] Creating shared instance of OEPocketsphinxController
    2018-05-01 13:50:04.030108-0700 BatchRecognizer[18593:7082913] Since there is no cached version, loading the language model lookup list for the acoustic model called AcousticModelEnglish
    2018-05-01 13:50:04.074654-0700 BatchRecognizer[18593:7082913] The word 10 was not found in the dictionary of the acoustic model /var/containers/Bundle/Application/54C1FE5C-4129-4196-9742-AAB180A9D0D2/BatchRecognizer.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.
    2018-05-01 13:50:04.077781-0700 BatchRecognizer[18593:7082913] Using convertGraphemes for the word or phrase 10 which doesn’t appear in the dictionary
    2018-05-01 13:50:04.082052-0700 BatchRecognizer[18593:7082913] Elapsed time to generate unknown word phonemes in English is 0.007310
    2018-05-01 13:50:04.082109-0700 BatchRecognizer[18593:7082913] the graphemes “T EH N” were created for the word 10 using the fallback method.
    2018-05-01 13:50:04.107354-0700 BatchRecognizer[18593:7082913] The word 20 was not found in the dictionary of the acoustic model /var/containers/Bundle/Application/54C1FE5C-4129-4196-9742-AAB180A9D0D2/BatchRecognizer.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.
    2018-05-01 13:50:04.107417-0700 BatchRecognizer[18593:7082913] Using convertGraphemes for the word or phrase 20 which doesn’t appear in the dictionary
    2018-05-01 13:50:04.108889-0700 BatchRecognizer[18593:7082913] Elapsed time to generate unknown word phonemes in English is 0.001500
    2018-05-01 13:50:04.108929-0700 BatchRecognizer[18593:7082913] the graphemes “T W EH N T IY” were created for the word 20 using the fallback method.
    2018-05-01 13:50:04.129393-0700 BatchRecognizer[18593:7082913] The word 30 was not found in the dictionary of the acoustic model /var/containers/Bundle/Application/54C1FE5C-4129-4196-9742-AAB180A9D0D2/BatchRecognizer.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.
    2018-05-01 13:50:04.129457-0700 BatchRecognizer[18593:7082913] Using convertGraphemes for the word or phrase 30 which doesn’t appear in the dictionary
    2018-05-01 13:50:04.129802-0700 BatchRecognizer[18593:7082913] Elapsed time to generate unknown word phonemes in English is 0.000373
    2018-05-01 13:50:04.129831-0700 BatchRecognizer[18593:7082913] the graphemes “TH ER D IY” were created for the word 30 using the fallback method.
    2018-05-01 13:50:04.149968-0700 BatchRecognizer[18593:7082913] I’m done running performDictionaryLookup and it took 0.114456 seconds
    2018-05-01 13:50:04.160065-0700 BatchRecognizer[18593:7082913] A request was made to set the path to the test file to the following path: /var/mobile/Containers/Data/Application/A110CE8A-F485-491C-9B3B-A4F903904CD8/Documents/Memo.wav
    2018-05-01 13:50:04.160149-0700 BatchRecognizer[18593:7082913] Attempting to start listening session from startListeningWithLanguageModelAtPath:
    2018-05-01 13:50:04.162066-0700 BatchRecognizer[18593:7082913] User gave mic permission for this app.
    2018-05-01 13:50:04.162213-0700 BatchRecognizer[18593:7082913] Valid setSecondsOfSilence value of 0.700000 will be used.
    2018-05-01 13:50:04.162575-0700 BatchRecognizer[18593:7083000] Starting listening.
    2018-05-01 13:50:04.162610-0700 BatchRecognizer[18593:7083000] About to set up audio session
    2018-05-01 13:50:04.290654-0700 BatchRecognizer[18593:7083007] Audio route has changed for the following reason:
    2018-05-01 13:50:04.297730-0700 BatchRecognizer[18593:7083007] There was a category change. The new category is AVAudioSessionCategoryPlayAndRecord
    2018-05-01 13:50:04.302228-0700 BatchRecognizer[18593:7083007] 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: 0x1d0009d00,
    inputs = (
    “<AVAudioSessionPortDescription: 0x1d0009e40, type = MicrophoneBuiltIn; name = iPhone Microphone; UID = Built-In Microphone; selectedDataSource = Front>”
    );
    outputs = (
    “<AVAudioSessionPortDescription: 0x1d000aa80, type = Speaker; name = Speaker; UID = Speaker; selectedDataSource = (null)>”
    )>”.
    2018-05-01 13:50:04.304586-0700 BatchRecognizer[18593:7083000] Creating audio session with default settings.
    2018-05-01 13:50:04.304614-0700 BatchRecognizer[18593:7083000] Done setting audio session category.
    2018-05-01 13:50:04.309007-0700 BatchRecognizer[18593:7083007] Audio route has changed for the following reason:
    2018-05-01 13:50:04.310917-0700 BatchRecognizer[18593:7083007] There was a category change. The new category is AVAudioSessionCategoryPlayAndRecord
    2018-05-01 13:50:04.323863-0700 BatchRecognizer[18593:7083000] Done setting preferred sample rate to 16000.000000 – now the real sample rate is 48000.000000
    2018-05-01 13:50:04.325927-0700 BatchRecognizer[18593:7083007] 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: 0x1d400dda0,
    inputs = (
    “<AVAudioSessionPortDescription: 0x1d400db40, type = MicrophoneBuiltIn; name = iPhone Microphone; UID = Built-In Microphone; selectedDataSource = Bottom>”
    );
    outputs = (
    “<AVAudioSessionPortDescription: 0x1d400e440, type = Receiver; name = Receiver; UID = Built-In Receiver; selectedDataSource = (null)>”
    )>”.
    2018-05-01 13:50:04.331294-0700 BatchRecognizer[18593:7083000] number of channels is already the preferred number of 1 so not setting it.
    2018-05-01 13:50:04.346941-0700 BatchRecognizer[18593:7083000] Done setting session’s preferred I/O buffer duration to 0.128000 – now the actual buffer duration is 0.085333
    2018-05-01 13:50:04.346995-0700 BatchRecognizer[18593:7083000] Done setting up audio session
    2018-05-01 13:50:04.360191-0700 BatchRecognizer[18593:7083000] 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.
    2018-05-01 13:50:04.388354-0700 BatchRecognizer[18593:7083000] Done setting up audio unit
    2018-05-01 13:50:04.388395-0700 BatchRecognizer[18593:7083000] About to start audio IO unit
    2018-05-01 13:50:04.532052-0700 BatchRecognizer[18593:7083000] Done starting audio unit
    INFO: pocketsphinx.c(145): Parsed model-specific feature parameters from /var/containers/Bundle/Application/54C1FE5C-4129-4196-9742-AAB180A9D0D2/BatchRecognizer.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/A110CE8A-F485-491C-9B3B-A4F903904CD8/Library/Caches/MyLanguageModel.dic
    -dictcase no no
    -dither no no
    -doublebw no no
    -ds 1 1
    -fdict /var/containers/Bundle/Application/54C1FE5C-4129-4196-9742-AAB180A9D0D2/BatchRecognizer.app/AcousticModelEnglish.bundle/noisedict
    -feat 1s_c_d_dd 1s_c_d_dd
    -featparams /var/containers/Bundle/Application/54C1FE5C-4129-4196-9742-AAB180A9D0D2/BatchRecognizer.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/54C1FE5C-4129-4196-9742-AAB180A9D0D2/BatchRecognizer.app/AcousticModelEnglish.bundle
    -input_endian little little
    -jsgf /var/mobile/Containers/Data/Application/A110CE8A-F485-491C-9B3B-A4F903904CD8/Library/Caches/MyLanguageModel.gram
    -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
    -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 1.000000e+00
    -maxhmmpf 30000 30000
    -maxwpf -1 -1
    -mdef /var/containers/Bundle/Application/54C1FE5C-4129-4196-9742-AAB180A9D0D2/BatchRecognizer.app/AcousticModelEnglish.bundle/mdef
    -mean /var/containers/Bundle/Application/54C1FE5C-4129-4196-9742-AAB180A9D0D2/BatchRecognizer.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/54C1FE5C-4129-4196-9742-AAB180A9D0D2/BatchRecognizer.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/54C1FE5C-4129-4196-9742-AAB180A9D0D2/BatchRecognizer.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/54C1FE5C-4129-4196-9742-AAB180A9D0D2/BatchRecognizer.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/54C1FE5C-4129-4196-9742-AAB180A9D0D2/BatchRecognizer.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/54C1FE5C-4129-4196-9742-AAB180A9D0D2/BatchRecognizer.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/54C1FE5C-4129-4196-9742-AAB180A9D0D2/BatchRecognizer.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/54C1FE5C-4129-4196-9742-AAB180A9D0D2/BatchRecognizer.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/54C1FE5C-4129-4196-9742-AAB180A9D0D2/BatchRecognizer.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/54C1FE5C-4129-4196-9742-AAB180A9D0D2/BatchRecognizer.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/54C1FE5C-4129-4196-9742-AAB180A9D0D2/BatchRecognizer.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/54C1FE5C-4129-4196-9742-AAB180A9D0D2/BatchRecognizer.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 4128 * 32 bytes (129 KiB) for word entries
    INFO: dict.c(333): Reading main dictionary: /var/mobile/Containers/Data/Application/A110CE8A-F485-491C-9B3B-A4F903904CD8/Library/Caches/MyLanguageModel.dic
    INFO: dict.c(213): Allocated 0 KiB for strings, 0 KiB for phones
    INFO: dict.c(336): 23 words read
    INFO: dict.c(358): Reading filler dictionary: /var/containers/Bundle/Application/54C1FE5C-4129-4196-9742-AAB180A9D0D2/BatchRecognizer.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: jsgf.c(691): Defined rule: <MyLanguageModel.g00000>
    INFO: jsgf.c(691): Defined rule: <MyLanguageModel.rule_0>
    INFO: jsgf.c(691): Defined rule: <MyLanguageModel.g00002>
    INFO: jsgf.c(691): Defined rule: <MyLanguageModel.rule_1>
    INFO: jsgf.c(691): Defined rule: <MyLanguageModel.g00004>
    INFO: jsgf.c(691): Defined rule: <MyLanguageModel.rule_2>
    INFO: jsgf.c(691): Defined rule: <MyLanguageModel.g00006>
    INFO: jsgf.c(691): Defined rule: <MyLanguageModel.rule_3>
    INFO: jsgf.c(691): Defined rule: <MyLanguageModel.g00008>
    INFO: jsgf.c(691): Defined rule: <MyLanguageModel.rule_4>
    INFO: jsgf.c(691): Defined rule: <MyLanguageModel.g00010>
    INFO: jsgf.c(691): Defined rule: <MyLanguageModel.g00011>
    INFO: jsgf.c(691): Defined rule: <MyLanguageModel.rule_5>
    INFO: jsgf.c(691): Defined rule: <MyLanguageModel.g00013>
    INFO: jsgf.c(691): Defined rule: <MyLanguageModel.rule_6>
    INFO: jsgf.c(691): Defined rule: <MyLanguageModel.g00015>
    INFO: jsgf.c(691): Defined rule: <MyLanguageModel.rule_7>
    INFO: jsgf.c(691): Defined rule: <MyLanguageModel.g00017>
    INFO: jsgf.c(691): Defined rule: PUBLIC <MyLanguageModel.rule_8>
    INFO: jsgf.c(359): Right recursion <MyLanguageModel.g00011> 11 => 7
    INFO: fsg_model.c(215): Computing transitive closure for null transitions
    INFO: fsg_model.c(277): 0 null transitions added
    INFO: fsg_search.c(227): FSG(beam: -1080, pbeam: -1080, wbeam: -634; wip: -5, pip: 0)
    INFO: fsg_model.c(428): Adding silence transitions for <sil> to FSG
    INFO: fsg_model.c(448): Added 16 silence word transitions
    INFO: fsg_model.c(428): Adding silence transitions for <sil> to FSG
    INFO: fsg_model.c(448): Added 16 silence word transitions
    INFO: fsg_model.c(428): Adding silence transitions for [BREATH] to FSG
    INFO: fsg_model.c(448): Added 16 silence word transitions
    INFO: fsg_model.c(428): Adding silence transitions for [COUGH] to FSG
    INFO: fsg_model.c(448): Added 16 silence word transitions
    INFO: fsg_model.c(428): Adding silence transitions for [NOISE] to FSG
    INFO: fsg_model.c(448): Added 16 silence word transitions
    INFO: fsg_model.c(428): Adding silence transitions for [SMACK] to FSG
    INFO: fsg_model.c(448): Added 16 silence word transitions
    INFO: fsg_model.c(428): Adding silence transitions for [UH] to FSG
    INFO: fsg_model.c(448): Added 16 silence word transitions
    INFO: fsg_search.c(173): Added 3 alternate word transitions
    INFO: fsg_lextree.c(110): Allocated 1504 bytes (1 KiB) for left and right context phones
    INFO: fsg_lextree.c(256): 268 HMM nodes in lextree (180 leaves)
    INFO: fsg_lextree.c(259): Allocated 38592 bytes (37 KiB) for all lextree nodes
    INFO: fsg_lextree.c(262): Allocated 25920 bytes (25 KiB) for lextree leafnodes
    2018-05-01 13:50:04.569363-0700 BatchRecognizer[18593:7083000] There is no CMN plist so we are using the fresh CMN value 40.000000.
    2018-05-01 13:50:04.569498-0700 BatchRecognizer[18593:7083000] Listening.
    2018-05-01 13:50:04.569721-0700 BatchRecognizer[18593:7083000] Project has these words or phrases in its dictionary:
    10
    20
    30
    COMPUTER
    DO
    EXECUTE
    FOLLOWING
    FORWARD
    GO
    GREETINGS
    HELLO
    HELLO(2)
    INSTRUCTION
    IT
    LEFT
    MOVE
    RIGHT
    ROBOT
    ROBOT(2)
    THANK
    THE
    THE(2)
    YOU
    2018-05-01 13:50:04.569745-0700 BatchRecognizer[18593:7083000] Recognition loop has started
    2018-05-01 13:50:04.569805-0700 BatchRecognizer[18593:7082913] Successfully started listening session from startListeningWithLanguageModelAtPath:
    Local callback: Pocketsphinx is now listening.
    Local callback: Pocketsphinx started.
    2018-05-01 13:50:04.906984-0700 BatchRecognizer[18593:7083000] Speech detected…
    Local callback: Pocketsphinx has detected speech.
    2018-05-01 13:50:06.268630-0700 BatchRecognizer[18593:7083000] End of speech detected…
    INFO: cmn_prior.c(131): cmn_prior_update: from < 40.00 0.00 0.00 0.00 Local callback: Pocketsphinx has detected a second of silence, concluding an utterance.
    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 < 27.37 2.62 -0.34 -3.00 0.25 8.42 5.90 -2.15 -5.91 -0.08 3.95 3.39 -2.00 >
    INFO: fsg_search.c(843): 155 frames, 5261 HMMs (33/fr), 11804 senones (76/fr), 608 history entries (3/fr)

    ERROR: “fsg_search.c”, line 913: Final result does not match the grammar in frame 155
    2018-05-01 13:50:06.270012-0700 BatchRecognizer[18593:7083000] Pocketsphinx heard “” with a score of (0) and an utterance ID of 0.
    2018-05-01 13:50:06.270099-0700 BatchRecognizer[18593:7083000] 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.
    INFO: fsg_search.c(1229): Start node DO.0:5:13
    INFO: fsg_search.c(1229): Start node <sil>.0:2:96
    INFO: fsg_search.c(1229): Start node <sil>.0:2:96
    INFO: fsg_search.c(1268): End node DO.149:154:154 (-1127)
    INFO: fsg_search.c(1268): End node <sil>.89:97:154 (-1087)
    INFO: fsg_search.c(1268): End node <sil>.89:97:154 (-1087)
    INFO: fsg_search.c(1268): End node <sil>.90:92:154 (-462)
    INFO: fsg_search.c(1492): lattice start node <s>.0 end node </s>.155
    2018-05-01 13:50:09.345677-0700 BatchRecognizer[18593:7083000] Speech detected…
    Local callback: Pocketsphinx has detected speech.
    INFO: cmn_prior.c(99): cmn_prior_update: from < 27.37 2.62 -0.34 -3.00 0.25 8.42 5.90 -2.15 -5.91 -0.08 3.95 3.39 -2.00 >
    INFO: cmn_prior.c(116): cmn_prior_update: to < 44.33 8.49 1.87 -3.03 -1.76 5.80 -2.52 -3.98 -3.79 4.42 0.81 -1.39 -1.15 >
    2018-05-01 13:50:17.118010-0700 BatchRecognizer[18593:7083000] End of speech detected…
    INFO: cmn_prior.c(131): cmn_prior_update: from < Local callback: Pocketsphinx has detected a second of silence, concluding an utterance.44.33
    8.49 1.87 -3.03 -1.76 5.80 -2.52 -3.98 -3.79 4.42 0.81 -1.39 -1.15 >
    INFO: cmn_prior.c(149): cmn_prior_update: to < 41.59 7.22 1.96 -1.59 -0.88 5.70 -1.83 -3.87 -2.90 3.83 0.61 -0.67 -1.30 >
    INFO: fsg_search.c(843): 785 frames, 22818 HMMs (29/fr), 52038 senones (66/fr), 3226 history entries (4/fr)

    2018-05-01 13:50:17.119378-0700 BatchRecognizer[18593:7083000] Pocketsphinx heard “HELLO COMPUTER DO THE FOLLOWING GO 10 LEFT EXECUTE THANK YOU” with a score of (0) and an utterance ID of 1.
    Local callback: The received hypothesis is HELLO COMPUTER DO THE FOLLOWING GO 10 LEFT EXECUTE THANK YOU with a score of 0 and an ID of 1
    INFO: fsg_search.c(1229): Start node HELLO(2).0:16:63
    INFO: fsg_search.c(1268): End node <sil>.731:733:784 (-493)
    INFO: fsg_search.c(1492): lattice start node HELLO(2).0 end node <sil>.731

    #1032430
    Halle Winkler
    Politepix

    Greetings,

    That’s normal for a grammar. Generally, scoring isn’t a useful/usable piece of info for your implementation.

Viewing 2 posts - 1 through 2 (of 2 total)
  • You must be logged in to reply to this topic.