本文主要是介绍语音识别基础篇(二) - pocketsphinx在windows下的编译和运行，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！
如需转载请标明出处：http://blog.csdn.net/itas109
QQ技术交流群：129518033
相关文章
语音识别基础篇(一) - CMU Sphinx简介
http://blog.csdn.net/itas109/article/details/78568591
1.编译环境
操作系统：windows 7 64Bit SP1
编译器：Viual Studio 2013
pocketsphinx版本：5prealpha
编译版本：Debug
下载地址：
CMU Sphinx - Browse /sphinxbase/5prealpha at SourceForge.net
CMU Sphinx - Browse /pocketsphinx/5prealpha at SourceForge.net
下载完成解压后目录如下图
2.编译sphinxbase
pocketsphinx依赖于sphinxbase，因此需要先编译sphinxbase。
使用VS2013打开sphinxbase.sln，直接点击生成解决方案即可
输出结果
3.编译pocketsphinx
使用VS2013打开pocketsphinx.sln，直接点击生成解决方案，结果报错了。。。
看错误估计是路径不对，然后右键pocketsphinx查看属性
经过查看果然路径有问题，将sphinxbase-master文件夹修改为sphinxbase文件夹，继续编译就通过了。
至此，pocketsphinx的编译工作结束了
4.运行
将sphinxbase.dll复制到pocketsphinx运行目录下，不然会报缺少DLL的错误。
如果有麦克风可以运行一下命令：
pocketsphinx_continuous.exe -inmic yes -hmm model\en-us\en-us -lm model\en-us\en-us.lm.bin -dict model\en-us\cmudict-en-us.dict也可以直接读取文件：
pocketsphinx_continuous.exe -infile test\data\goforward.raw -hmm model\en-us\en-us -lm model\en-us\en-us.lm.bin -dict model\en-us\cmudict-en-us.dict
这里我们使用文件来运行：
pocketsphinx_continuous.exe -infile D
:\ASR\pocketsphinx-master\test\data\cards\004.wav -hmm D:\ASR\pocketsphinx-maste
r\model\en-us\en-us -lm D:\ASR\pocketsphinx-master\model\en-us\en-us.lm.bin -dic
t D:\ASR\pocketsphinx-master\model\en-us\cmudict-en-us.dict
运行结果如下：
D:\ASR\pocketsphinx-master\bin\Debug\Win32>pocketsphinx_continuous.exe -infile D
:\ASR\pocketsphinx-master\test\data\cards\004.wav -hmm D:\ASR\pocketsphinx-maste
r\model\en-us\en-us -lm D:\ASR\pocketsphinx-master\model\en-us\en-us.lm.bin -dic
t D:\ASR\pocketsphinx-master\model\en-us\cmudict-en-us.dict
INFO: pocketsphinx.c(152): Parsed model-specific feature parameters from D:\ASR\
pocketsphinx-master\model\en-us\en-us/feat.params
Current configuration:
[NAME] [DEFLT] [VALUE]
-agc none none
-agcthresh 2.0 2.000000e+000
-allphone
-allphone_ci yes yes
-alpha 0.97 9.700000e-001
-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
-ceplen 13 13
-cmn live batch
-cmninit 40,3,-1 41.00,-5.29,-0.12,5.09,2.48,-4.07,-1.37,
-1.78,-5.08,-2.05,-6.45,-1.42,1.17
-compallsen no no
-dict D:\ASR\pocketsphinx-master\model\en-us\c
mudict-en-us.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:\ASR\pocketsphinx-master\model\en-us\e
n-us
-input_endian little little
-jsgf
-keyphrase
-kws
-kws_delay 10 10
-kws_plp 1e-1 1.000000e-001
-kws_threshold 1e-30 1.000000e-030
-latsize 5000 5000
-lda
-ldadim 0 0
-lifter 0 22
-lm D:\ASR\pocketsphinx-master\model\en-us\e
n-us.lm.bin
-lmctl
-lmname
-logbase 1.0001 1.000100e+000
-logfn
-logspec no no
-lowerf 133.33334 1.300000e+002
-lpbeam 1e-40 1.000000e-040
-lponlybeam 7e-29 7.000000e-029
-lw 6.5 6.500000e+000
-maxhmmpf 30000 30000
-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 25
-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-10 1.000000e-010
-pl_pip 1.0 1.000000e+000
-pl_weight 3.0 3.000000e+000
-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+004
-seed -1 -1
-sendump
-senlogdir
-senmgau
-silprob 0.005 5.000000e-003
-smoothspec no no
-svspec 0-12/13-25/26-38
-tmat
-tmatfloor 0.0001 1.000000e-004
-topn 4 4
-topn_beam 0 0
-toprule
-transform legacy dct
-unit_area yes yes
-upperf 6855.4976 6.800000e+003
-uw 1.0 1.000000e+000
-vad_postspeech 50 50
-vad_prespeech 20 20
-vad_startspeech 10 10
-vad_threshold 3.0 3.000000e+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-002INFO: feat.c(715): Initializing feature stream to type: '1s_c_d_dd', ceplen=13,
CMN='batch', VARNORM='no', AGC='none'
INFO: acmod.c(162): Using subvector specification 0-12/13-25/26-38
INFO: mdef.c(518): Reading model definition: D:\ASR\pocketsphinx-master\model\en
-us\en-us/mdef
INFO: mdef.c(531): Found byte-order mark BMDF, assuming this is a binary mdef fi
le
INFO: bin_mdef.c(336): Reading binary model definition: D:\ASR\pocketsphinx-mast
er\model\en-us\en-us/mdef
INFO: bin_mdef.c(516): 42 CI-phone, 137053 CD-phone, 3 emitstate/phone, 126 CI-s
en, 5126 Sen, 29324 Sen-Seq
INFO: tmat.c(149): Reading HMM transition probability matrices: D:\ASR\pocketsph
inx-master\model\en-us\en-us/transition_matrices
INFO: acmod.c(113): Attempting to use PTM computation module
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: D:\ASR\pocketsphinx-
master\model\en-us\en-us/means
INFO: ms_gauden.c(242): 42 codebook, 3 feature, size:
INFO: ms_gauden.c(244): 128x13
INFO: ms_gauden.c(244): 128x13
INFO: ms_gauden.c(244): 128x13
INFO: ms_gauden.c(127): Reading mixture gaussian parameter: D:\ASR\pocketsphinx-
master\model\en-us\en-us/variances
INFO: ms_gauden.c(242): 42 codebook, 3 feature, size:
INFO: ms_gauden.c(244): 128x13
INFO: ms_gauden.c(244): 128x13
INFO: ms_gauden.c(244): 128x13
INFO: ms_gauden.c(304): 222 variance values floored
INFO: ptm_mgau.c(475): Loading senones from dump file D:\ASR\pocketsphinx-master
\model\en-us\en-us/sendump
INFO: ptm_mgau.c(499): BEGIN FILE FORMAT DESCRIPTION
INFO: ptm_mgau.c(562): Rows: 128, Columns: 5126
INFO: ptm_mgau.c(594): Using memory-mapped I/O for senones
INFO: ptm_mgau.c(837): Maximum top-N: 4
INFO: phone_loop_search.c(114): State beam -225 Phone exit beam -225 Insertion p
enalty 0
INFO: dict.c(320): Allocating 138824 * 20 bytes (2711 KiB) for word entries
INFO: dict.c(333): Reading main dictionary: D:\ASR\pocketsphinx-master\model\en-
us\cmudict-en-us.dict
INFO: dict.c(213): Dictionary size 134723, allocated 1016 KiB for strings, 1679
KiB for phones
INFO: dict.c(336): 134723 words read
INFO: dict.c(358): Reading filler dictionary: D:\ASR\pocketsphinx-master\model\e
n-us\en-us/noisedict
INFO: dict.c(213): Dictionary size 134728, allocated 0 KiB for strings, 0 KiB fo
r phones
INFO: dict.c(361): 5 words read
INFO: dict2pid.c(396): Building PID tables for dictionary
INFO: dict2pid.c(406): Allocating 42^3 * 2 bytes (144 KiB) for word-initial trip
hones
INFO: dict2pid.c(132): Allocated 21336 bytes (20 KiB) for word-final triphones
INFO: dict2pid.c(196): Allocated 21336 bytes (20 KiB) for single-phone word trip
hones
INFO: ngram_model_trie.c(354): Trying to read LM in trie binary format
INFO: ngram_search_fwdtree.c(74): Initializing search tree
INFO: ngram_search_fwdtree.c(101): 791 unique initial diphones
INFO: ngram_search_fwdtree.c(186): Creating search channels
INFO: ngram_search_fwdtree.c(323): Max nonroot chan increased to 152609
INFO: ngram_search_fwdtree.c(333): Created 723 root, 152481 non-root channels, 5
3 single-phone words
INFO: ngram_search_fwdflat.c(157): fwdflat: min_ef_width = 4, max_sf_win = 25
INFO: continuous.c(307): pocketsphinx_continuous.exe COMPILED ON: Nov 20 2017, A
T: 20:33:32INFO: cmn_live.c(120): Update from < 41.00 -5.29 -0.12 5.09 2.48 -4.07 -1.37 -
1.78 -5.08 -2.05 -6.45 -1.42 1.17 >
INFO: cmn_live.c(138): Update to < 64.76 -3.10 -9.74 0.89 -10.79 -0.03 -8.38
-4.40 -7.83 7.06 -2.24 5.81 -2.96 >
INFO: ngram_search_fwdtree.c(1550): 4674 words recognized (30/fr)
INFO: ngram_search_fwdtree.c(1552): 494454 senones evaluated (3190/fr)
INFO: ngram_search_fwdtree.c(1556): 3563622 channels searched (22991/fr), 864781st, 209626 last
INFO: ngram_search_fwdtree.c(1559): 9899 words for which last channels evalu
ated (63/fr)
INFO: ngram_search_fwdtree.c(1561): 460667 candidate words for entering last p
hone (2972/fr)
INFO: ngram_search_fwdtree.c(1564): fwdtree 3.87 CPU 2.496 xRT
INFO: ngram_search_fwdtree.c(1567): fwdtree 3.87 wall 2.495 xRT
INFO: ngram_search_fwdflat.c(302): Utterance vocabulary contains 176 words
INFO: ngram_search_fwdflat.c(948): 2436 words recognized (16/fr)
INFO: ngram_search_fwdflat.c(950): 189379 senones evaluated (1222/fr)
INFO: ngram_search_fwdflat.c(952): 291055 channels searched (1877/fr)
INFO: ngram_search_fwdflat.c(954): 14721 words searched (94/fr)
INFO: ngram_search_fwdflat.c(957): 11844 word transitions (76/fr)
INFO: ngram_search_fwdflat.c(960): fwdflat 0.33 CPU 0.211 xRT
INFO: ngram_search_fwdflat.c(963): fwdflat 0.32 wall 0.209 xRT
INFO: ngram_search.c(1250): lattice start node <s>.0 end node </s>.125
INFO: ngram_search.c(1276): Eliminated 1 nodes before end node
INFO: ngram_search.c(1381): Lattice has 511 nodes, 1221 links
INFO: ps_lattice.c(1374): Bestpath score: -4996
INFO: ps_lattice.c(1378): Normalizer P(O) = alpha(</s>:125:153) = -402730
INFO: ps_lattice.c(1435): Joint P(O,S) = -415426 P(S|O) = -12696
INFO: ngram_search.c(872): bestpath 0.02 CPU 0.010 xRT
INFO: ngram_search.c(875): bestpath 0.01 wall 0.008 xRT
five five
INFO: ngram_search_fwdtree.c(429): TOTAL fwdtree 3.87 CPU 2.512 xRT
INFO: ngram_search_fwdtree.c(432): TOTAL fwdtree 3.87 wall 2.511 xRT
INFO: ngram_search_fwdflat.c(176): TOTAL fwdflat 0.33 CPU 0.213 xRT
INFO: ngram_search_fwdflat.c(179): TOTAL fwdflat 0.32 wall 0.210 xRT
INFO: ngram_search.c(303): TOTAL bestpath 0.02 CPU 0.010 xRT
INFO: ngram_search.c(306): TOTAL bestpath 0.01 wall 0.008 xRT
我们在倒数7行看到了five five。这就是识别结果。
在下一篇里面我们将介绍一下中文语音识别。
Reference:
Building an application with PocketSphinx – CMUSphinx Open Source Speech Recognition
觉得文章对你有帮助，可以用微信扫描二维码捐赠给博主，谢谢！
如需转载请标明出处：http://blog.csdn.net/itas109
QQ技术交流群：12951803
这篇关于语音识别基础篇(二) - pocketsphinx在windows下的编译和运行的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！
