Maximum duration of File to cross check voice
GoogleCodeExporter opened this issue · 2 comments
GoogleCodeExporter commented
Four wav files with following specifications :
codec : PCM s16 LE(araw)
channels : Mono
Sample rate : 8000 Hz
Bits per sample : 16
with the help of sox removing silence & with one wav file built model
vid = "vid" + " -s " + MR549a7b54b7143a42d04eaa69 + " -g " + wavfile
proc = subprocess.call([vid], shell=True)
------------- MR549a7b54b7143a42d04eaa69.gmm.
Trying to Find voice match with remaining wav files by following :
-----------vid = "vid -i " + wavfile + " -f json -n -u"
subprocess.call([vid], shell=True)
out of remaining three wav files , two had duration above 1min 30 seconds and
other had only 25 sec of duration.
problems?
1. For the duration of 25 sec wav file , it gives me The system identified this
speaker as wrong id. Ex : 'MR54585b7de75e4a1c58fc0785'!
What is the expected output? What do you see instead?
Should match same voice identification.
What version of the product are you using? On what operating system?
Centos 6.6
Please provide any additional information below.
Original issue reported on code.google.com by dharani....@coartha.com on 3 Jul 2015 at 1:49
Attachments:
GoogleCodeExporter commented
Each wav file is having only one speaker, but it is looking for multiple
speakers and for few wav files it is showing as different speakers like S0 :
speaker1, S10 : speaker2 and S6 : actual speaker.
Original comment by dharani....@coartha.com on 8 Jul 2015 at 12:37
GoogleCodeExporter commented
S_5577d2d7c3ed04936cb43e38_9177007747_5576c759b1e627ce0ef39207.wav
converting_file
diarization
trimming
voice matching
extraction finished
**********************************
speaker S3
MR557bda96c3ed04936cb43e79 -33.3603964948
MR549a7bb7b7143a42d04eaa6c -33.7316351482
MR5577cf2cc3ed04936cb43e31 -32.9864307262
MR5575a739f498062c23b9c705 -33.0839068014
MR549a7b54b7143a42d04eaa69 -33.7912145021
MR54c0a1dee75e4a49303b5138 -33.8746924564
MR5575a739f498062c23b9c7cf -33.0221918751
MR554b0828d428e52c792e0491 -32.9209118031
MR5279e49de75e4a490d13aea0 -33.8218110018
MR557a73fdc3ed04936cb43e70 -33.0859611666
MR5577d809c3ed04936cb43e3e -32.7342142111
MR557ab376c3ed04936cb43e75 -32.4454878669
MR5575a735f498062c23b9bc73 -33.1727626017
MR5575a736f498062c23b9bf59 -33.0491286459
MR5576c58ef498062c23b9d132 -33.2237084807
MR5576c58cf498062c23b9d0ec -32.9413484339
MR55793e86c3ed04936cb43e66 -32.8526830159
MR5458a87fe75e4a02f2f4b945 -33.646783521
MR5575a735f498062c23b9bc16 -33.0580896961
MR557edba6c3ed04936cb43e84 -32.6540488107
MR55840737c3ed04936cb43e95 -32.1961454795
MR54b3584f4787f3941fd447b3 -32.9644933284
MR55758472c3ed04936cb43e0e -32.9176104352
MR5575a738f498062c23b9c482 -32.6669171268
MR54585b7de75e4a1c58fc0785 -33.8489164319
MR5575a737f498062c23b9c1ed -32.6439562207
MR5576c5cef498062c23b9d4dc -32.7875406211
MR54ec758a694b740848e4aae6 -33.6639167078
MR5571847cf498062c23b9abab -33.445850947
MR557a8166c3ed04936cb43e73 -33.0836662506
MR5576c5cef498062c23b9d4d9 -33.1654058533
MR5577c625c3ed04936cb43e23 -32.4970319164
MR5575a736f498062c23b9bed1 -32.8659237612
MR5577d2d7c3ed04936cb43e38 -32.9445391368
MR5576c58bf498062c23b9d099 -33.2020016713
MR5577e161c3ed04936cb43e44 -33.2028401067
MR54c0a1dee75e4a49303b513a -33.5278010595
------------------------
best speaker: S3 (MR55840737c3ed04936cb43e95) (distance from 2nd 0.249342 - mean -33.110323 - distance from mean 0.914178 )
**********************************
speaker S2
MR557bda96c3ed04936cb43e79 -31.9513434906
MR549a7bb7b7143a42d04eaa6c -32.212020484
MR5577cf2cc3ed04936cb43e31 -31.8095796577
MR5575a739f498062c23b9c705 -31.7837056923
MR549a7b54b7143a42d04eaa69 -32.0798612224
MR55793e86c3ed04936cb43e66 -31.5572575455
MR557a8166c3ed04936cb43e73 -31.547140835
MR554b0828d428e52c792e0491 -31.665722123
MR5279e49de75e4a490d13aea0 -32.1752855062
MR557a73fdc3ed04936cb43e70 -31.815076862
MR5577d809c3ed04936cb43e3e -31.6064481975
MR557ab376c3ed04936cb43e75 -31.4764366866
MR5575a735f498062c23b9bc73 -31.6494616601
MR5575a736f498062c23b9bf59 -31.9614915039
MR5576c58ef498062c23b9d132 -31.569837197
MR54c0a1dee75e4a49303b5138 -32.0908845811
MR5458a87fe75e4a02f2f4b945 -31.9526767588
MR5575a735f498062c23b9bc16 -31.7165042367
MR54c0a1dee75e4a49303b513a -31.8949458316
MR55840737c3ed04936cb43e95 -31.1635332088
MR54b3584f4787f3941fd447b3 -31.6640975052
MR55758472c3ed04936cb43e0e -31.4990789535
MR5575a738f498062c23b9c482 -31.5768601868
MR54585b7de75e4a1c58fc0785 -32.2821207584
MR5575a737f498062c23b9c1ed -31.3298645823
MR5577c625c3ed04936cb43e23 -31.5238796947
MR5576c5cef498062c23b9d4dc -31.7048500261
MR54ec758a694b740848e4aae6 -31.8956835923
MR5571847cf498062c23b9abab -32.0408342253
MR5575a739f498062c23b9c7cf -31.8714336661
MR5576c5cef498062c23b9d4d9 -31.7881537171
MR5577e161c3ed04936cb43e44 -31.7669370232
MR5575a736f498062c23b9bed1 -31.6809025655
MR5577d2d7c3ed04936cb43e38 -31.3420171607
MR5576c58bf498062c23b9d099 -31.6716939443
MR5576c58cf498062c23b9d0ec -31.5751849164
MR557edba6c3ed04936cb43e84 -31.3085006844
------------------------
best speaker: S2 (MR55840737c3ed04936cb43e95) (distance from 2nd 0.144967 - mean -31.735170 - distance from mean 0.571637 )
**********************************
speaker S1
MR557bda96c3ed04936cb43e79 -34.637608789
MR549a7bb7b7143a42d04eaa6c -34.938248145
MR5577cf2cc3ed04936cb43e31 -34.1683535371
MR5575a739f498062c23b9c705 -34.1434403069
MR549a7b54b7143a42d04eaa69 -34.8546407825
MR55793e86c3ed04936cb43e66 -33.8937430036
MR557a8166c3ed04936cb43e73 -32.93487433
MR554b0828d428e52c792e0491 -34.1355821062
MR5279e49de75e4a490d13aea0 -35.0212594494
MR557a73fdc3ed04936cb43e70 -34.3446041966
MR5577d809c3ed04936cb43e3e -33.771165383
MR557ab376c3ed04936cb43e75 -33.7933753982
MR5575a735f498062c23b9bc73 -34.1537101626
MR5575a736f498062c23b9bf59 -34.328863482
MR5576c58ef498062c23b9d132 -34.3288218097
MR54c0a1dee75e4a49303b5138 -34.8312301323
MR5458a87fe75e4a02f2f4b945 -34.601940794
MR5575a735f498062c23b9bc16 -34.0530871536
MR557edba6c3ed04936cb43e84 -33.4124062095
MR55840737c3ed04936cb43e95 -33.2648468724
MR54b3584f4787f3941fd447b3 -33.9206676065
MR55758472c3ed04936cb43e0e -34.0354910533
MR5575a738f498062c23b9c482 -33.4575611198
MR54585b7de75e4a1c58fc0785 -34.7649531835
MR5575a737f498062c23b9c1ed -33.833807805
MR5577c625c3ed04936cb43e23 -33.6611110535
MR5576c5cef498062c23b9d4dc -33.8888859363
MR54ec758a694b740848e4aae6 -34.8973263245
MR5571847cf498062c23b9abab -34.8274263521
MR5575a739f498062c23b9c7cf -34.414802775
MR5576c5cef498062c23b9d4d9 -34.2566656487
MR5577e161c3ed04936cb43e44 -34.0899354721
MR5575a736f498062c23b9bed1 -34.0041392389
MR5577d2d7c3ed04936cb43e38 -33.3127779883
MR5576c58bf498062c23b9d099 -34.4091048702
MR5576c58cf498062c23b9d0ec -33.853240936
MR54c0a1dee75e4a49303b513a -34.5336801538
------------------------
best speaker: S1 (MR557a8166c3ed04936cb43e73) (distance from 2nd 0.329973 - mean -34.156037 - distance from mean 1.221163 )
**********************************
speaker S0
MR557bda96c3ed04936cb43e79 -26.0508622832
MR549a7bb7b7143a42d04eaa6c -26.3656372394
MR5577cf2cc3ed04936cb43e31 -26.0417139832
MR5575a739f498062c23b9c705 -26.0523406766
MR549a7b54b7143a42d04eaa69 -26.5726893978
MR54c0a1dee75e4a49303b5138 -26.4651982847
MR557a8166c3ed04936cb43e73 -25.5621302387
MR554b0828d428e52c792e0491 -25.7757608609
MR5279e49de75e4a490d13aea0 -26.4917998016
MR557a73fdc3ed04936cb43e70 -26.0964830604
MR5577d809c3ed04936cb43e3e -25.989553595
MR557ab376c3ed04936cb43e75 -25.6774092974
MR5575a735f498062c23b9bc73 -26.0256650928
MR5575a736f498062c23b9bf59 -26.0433750295
MR5576c58ef498062c23b9d132 -26.104736774
MR5576c58cf498062c23b9d0ec -25.9720309559
MR55793e86c3ed04936cb43e66 -25.9021382627
MR5458a87fe75e4a02f2f4b945 -26.2599751065
MR5575a735f498062c23b9bc16 -26.1235340063
MR54c0a1dee75e4a49303b513a -26.0881288139
MR55840737c3ed04936cb43e95 -25.7450589407
MR54b3584f4787f3941fd447b3 -26.1056283965
MR55758472c3ed04936cb43e0e -26.0959841781
MR5575a738f498062c23b9c482 -25.5485673553
MR54585b7de75e4a1c58fc0785 -26.1899663681
MR5575a737f498062c23b9c1ed -25.7266979496
MR5576c5cef498062c23b9d4dc -25.9544626737
MR54ec758a694b740848e4aae6 -26.1701357884
MR5571847cf498062c23b9abab -26.1108641414
MR5575a739f498062c23b9c7cf -26.1422972408
MR5576c5cef498062c23b9d4d9 -25.9692535986
MR5577c625c3ed04936cb43e23 -25.9114547448
MR5575a736f498062c23b9bed1 -25.9681262767
MR5577d2d7c3ed04936cb43e38 -25.6575589494
MR5576c58bf498062c23b9d099 -26.2380375865
MR5577e161c3ed04936cb43e44 -26.1536434278
MR557edba6c3ed04936cb43e84 -25.8657376711
------------------------
best speaker: S0 (unknown) (distance from 2nd 0.013563 - mean -26.032828 - distance from mean 0.484261 )
**********************************
speaker S7
MR557bda96c3ed04936cb43e79 -31.0890601845
MR549a7bb7b7143a42d04eaa6c -31.5169610233
MR5577cf2cc3ed04936cb43e31 -30.9051693308
MR5575a739f498062c23b9c705 -30.7079625795
MR549a7b54b7143a42d04eaa69 -31.383910033
MR55793e86c3ed04936cb43e66 -30.7008878525
MR5575a739f498062c23b9c7cf -30.7618251069
MR554b0828d428e52c792e0491 -30.8268799811
MR5279e49de75e4a490d13aea0 -31.4555433312
MR557a73fdc3ed04936cb43e70 -31.0112755101
MR54ec758a694b740848e4aae6 -31.2876231698
MR5577d809c3ed04936cb43e3e -30.871931394
MR557ab376c3ed04936cb43e75 -30.45949601
MR5575a735f498062c23b9bc73 -30.7497268761
MR5575a736f498062c23b9bed1 -30.6307721172
MR5576c58ef498062c23b9d132 -30.6913883326
MR5576c58cf498062c23b9d0ec -30.3569707436
MR54c0a1dee75e4a49303b5138 -31.4153164765
MR5458a87fe75e4a02f2f4b945 -31.2025247304
MR5575a735f498062c23b9bc16 -30.6659447857
MR5576c5cef498062c23b9d4dc -30.7426721824
MR55840737c3ed04936cb43e95 -30.3274746886
MR54b3584f4787f3941fd447b3 -30.8165596276
MR55758472c3ed04936cb43e0e -30.6223050714
MR5575a738f498062c23b9c482 -30.6161129781
MR54585b7de75e4a1c58fc0785 -31.6269207502
MR5575a737f498062c23b9c1ed -30.4679760464
MR5575a736f498062c23b9bf59 -30.9842976837
MR5571847cf498062c23b9abab -31.1786895944
MR557a8166c3ed04936cb43e73 -30.8152863761
MR5576c5cef498062c23b9d4d9 -30.8586350853
MR54c0a1dee75e4a49303b513a -31.1775528537
MR5577c625c3ed04936cb43e23 -30.3667470004
MR5577d2d7c3ed04936cb43e38 -30.3773292279
MR5576c58bf498062c23b9d099 -30.9673524179
MR5577e161c3ed04936cb43e44 -30.6252233156
MR557edba6c3ed04936cb43e84 -30.0788794066
------------------------
best speaker: S7 (MR557edba6c3ed04936cb43e84) (distance from 2nd 0.248595 - mean -30.847059 - distance from mean 0.768180 )
**********************************
speaker S5
MR557bda96c3ed04936cb43e79 -34.7967532981
MR549a7bb7b7143a42d04eaa6c -35.1610138842
MR5577cf2cc3ed04936cb43e31 -34.3491799864
MR5575a739f498062c23b9c705 -34.2825807738
MR549a7b54b7143a42d04eaa69 -35.125094469
MR55793e86c3ed04936cb43e66 -34.2387530427
MR557a8166c3ed04936cb43e73 -34.3298718938
MR554b0828d428e52c792e0491 -34.3058384
MR5279e49de75e4a490d13aea0 -35.2491658658
MR557a73fdc3ed04936cb43e70 -34.5242899949
MR5575a736f498062c23b9bf59 -34.4675556573
MR5577d809c3ed04936cb43e3e -34.0793452526
MR557ab376c3ed04936cb43e75 -33.7352604029
MR5575a735f498062c23b9bc73 -34.526509365
MR5575a736f498062c23b9bed1 -34.1697888932
MR5576c58ef498062c23b9d132 -34.4362433078
MR5576c58cf498062c23b9d0ec -33.9954549659
MR54c0a1dee75e4a49303b5138 -35.1193638019
MR5458a87fe75e4a02f2f4b945 -35.0118959103
MR5575a735f498062c23b9bc16 -34.2821595797
MR5576c5cef498062c23b9d4dc -34.2333438479
MR55840737c3ed04936cb43e95 -33.1127308294
MR54b3584f4787f3941fd447b3 -34.3758577942
MR55758472c3ed04936cb43e0e -34.1715690015
MR5575a738f498062c23b9c482 -33.7214208071
MR54585b7de75e4a1c58fc0785 -35.2007704633
MR5575a737f498062c23b9c1ed -33.9055690243
MR54ec758a694b740848e4aae6 -35.1226692541
MR5571847cf498062c23b9abab -35.0242700693
MR5575a739f498062c23b9c7cf -34.2077642042
MR5576c5cef498062c23b9d4d9 -34.4534065296
MR5577c625c3ed04936cb43e23 -33.6263200091
MR5577d2d7c3ed04936cb43e38 -33.8639313605
MR5576c58bf498062c23b9d099 -34.6534543079
MR5577e161c3ed04936cb43e44 -34.2847529484
MR54c0a1dee75e4a49303b513a -34.9468502632
MR557edba6c3ed04936cb43e84 -33.5285631537
------------------------
best speaker: S5 (MR55840737c3ed04936cb43e95) (distance from 2nd 0.415832 - mean -34.395118 - distance from mean 1.282387 )
**********************************
speaker S4
MR557bda96c3ed04936cb43e79 -34.4104806209
MR549a7bb7b7143a42d04eaa6c -34.8426276268
MR5577cf2cc3ed04936cb43e31 -34.080090846
MR5575a739f498062c23b9c705 -34.1528576628
MR549a7b54b7143a42d04eaa69 -34.7820566318
MR55793e86c3ed04936cb43e66 -33.7633603852
MR5575a739f498062c23b9c7cf -34.0649851498
MR554b0828d428e52c792e0491 -34.0437732885
MR5279e49de75e4a490d13aea0 -34.9282708748
MR557a73fdc3ed04936cb43e70 -34.122664173
MR5577d809c3ed04936cb43e3e -33.7344954239
MR557ab376c3ed04936cb43e75 -33.6070317812
MR5575a735f498062c23b9bc73 -34.2395983632
MR5575a736f498062c23b9bf59 -34.089913716
MR5576c58ef498062c23b9d132 -34.2485378451
MR54c0a1dee75e4a49303b5138 -34.719943346
MR5458a87fe75e4a02f2f4b945 -34.5826339438
MR5575a735f498062c23b9bc16 -33.9831962935
MR5576c5cef498062c23b9d4dc -33.9334337028
MR55840737c3ed04936cb43e95 -33.2529110601
MR54b3584f4787f3941fd447b3 -33.9374507546
MR55758472c3ed04936cb43e0e -33.9237762065
MR5575a738f498062c23b9c482 -33.7052767615
MR54585b7de75e4a1c58fc0785 -34.8932350311
MR5575a737f498062c23b9c1ed -33.5848967174
MR5577c625c3ed04936cb43e23 -33.4533659695
MR54ec758a694b740848e4aae6 -34.7922987201
MR5571847cf498062c23b9abab -34.5370554483
MR557a8166c3ed04936cb43e73 -34.1400570378
MR5576c5cef498062c23b9d4d9 -34.2261945474
MR54c0a1dee75e4a49303b513a -34.5998046683
MR5577e161c3ed04936cb43e44 -34.1121848802
MR5575a736f498062c23b9bed1 -33.8672980117
MR5577d2d7c3ed04936cb43e38 -33.9270306576
MR5576c58bf498062c23b9d099 -34.3522510036
MR5576c58cf498062c23b9d0ec -33.9302961271
MR557edba6c3ed04936cb43e84 -33.42906943
------------------------
best speaker: S4 (unknown) (distance from 2nd 0.176158 - mean -34.134984 - distance from mean 0.882073 )
wav duration: 00:00:59,000
all done in 642sec (00:10:42,947) (diarization 69sec time:00:01:09,581 ) with
1 threads and 57 voices in db (191.122031)
S3 (MR55840737c3ed04936cb43e95)
/home/coartha/Videos/firstbatch/S_5577d2d7c3ed04936cb43e38_9177007747_5576c759b1
e627ce0ef39207_/S3.wav
00:00:21,970 to 00:00:27,370
S2 (MR55840737c3ed04936cb43e95)
/home/coartha/Videos/firstbatch/S_5577d2d7c3ed04936cb43e38_9177007747_5576c759b1
e627ce0ef39207_/S2.wav
00:00:18,550 to 00:00:21,410
S1 (MR557a8166c3ed04936cb43e73)
/home/coartha/Videos/firstbatch/S_5577d2d7c3ed04936cb43e38_9177007747_5576c759b1
e627ce0ef39207_/S1.wav
00:00:02,330 to 00:00:11,100
S0 (unknown)
/home/coartha/Videos/firstbatch/S_5577d2d7c3ed04936cb43e38_9177007747_5576c759b1
e627ce0ef39207_/S0.wav
00:00:00,570 to 00:00:02,330
S7 (MR557edba6c3ed04936cb43e84)
/home/coartha/Videos/firstbatch/S_5577d2d7c3ed04936cb43e38_9177007747_5576c759b1
e627ce0ef39207_/S7.wav
00:00:46,540 to 00:00:49,300
S5 (MR55840737c3ed04936cb43e95)
/home/coartha/Videos/firstbatch/S_5577d2d7c3ed04936cb43e38_9177007747_5576c759b1
e627ce0ef39207_/S5.wav
00:00:30,510 to 00:00:34,360
00:00:35,920 to 00:00:37,590
S4 (unknown)
/home/coartha/Videos/firstbatch/S_5577d2d7c3ed04936cb43e38_9177007747_5576c759b1
e627ce0ef39207_/S4.wav
00:00:27,370 to 00:00:30,510
Original comment by dharani....@coartha.com on 8 Jul 2015 at 12:40