window下基于VS，CMUSphinx的中文小词汇量语音识别实例

window下基于VS，CMUSphinx的中文小词汇量语音识别实例

用到的工具包：

1. sphinxbase

2. pocketshinx-5prealpha

3. zh_broadcastnews_16k_ptm256_8000

这是我第一次做语音识别的相关项目，学习来自http://blog.csdn.net/itas109 的教程。虽然英文的语音识别没有做出了，但是中文的出来了！！！开心

语音识别（一）前期资料了解：

https://blog.csdn.net/itas109/article/details/78568591

语音识别（二）：英文语音识别，按照下面链接中这位大神的详细指导完成

https://blog.csdn.net/itas109/article/details/78586730

但是本人在 4.运行 部分没有成功，出现错误如下：
运行 cmd：

G:\_Test\my_speech_recognition\pocketsphinx-5prealpha\bin\Debug\Win32>pocketsphinx_continuous.exe -infile G:\_Test\my_speech_recognition\pocketsphinx-5prealpha\test\data\cards\004.wav -hmm G:\_Test\my_speech_recognition\pocketsphinx-5prealpha\model\en-us\en-us -lm ?G:\_Test\my_speech_recognition\pocketsphinx-5prealpha\model\en-us\en-us.lm.bin -dict G:\_Test\my_speech_recognition\pocketsphinx-5prealpha\model\en-us\cmudict-en-us.dict
INFO: pocketsphinx.c(152): Parsed model-specific feature parameters from G:\_Test\my_speech_recognition\pocketsphinx-5prealpha\model\en-us\en-us/feat.params
Current configuration:

出错了：

   INFO: ngram_model_trie.c(354): Trying to read LM in trie binary format 
   ERROR: "ngram_model_trie.c", line 356: File ?G:\_Test\my_speech_recognition\pocketsphinx-5prealpha\model\en-us\en-us.lm.bin not found
   INFO: ngram_model_trie.c(177): Trying to read LM in arpa format
   ERROR: "ngram_model_trie.c", line 179: File ?G:\_Test\my_speech_recognition\pocketsphinx-5prealpha\model\en-us\en-us.lm.bin not found
   INFO: ngram_model_trie.c(445): Trying to read LM in dmp format 
   ERROR: "ngram_model_trie.c", line 447: Dump file ?G:\_Test\my_speech_recognition\pocketsphinx-5prealpha\model\en-us\en-us.lm.bin not found

由于时间紧迫，纠结了半天之后，直接跳过这个部分，开始中文语音识别。

语音识别（三）中文语音识别

https://blog.csdn.net/itas109/article/details/78999477

我cmd的命令是：

G:\_Test\my_speech_recognition\pocketsphinx-5prealpha\bin\Debug\Win32>pocketsphinx_continuous -inmic yes -hmm zh_broadcastnews_16k_ptm256_8000 -lm a.lm -dict a.dic
INFO: pocketsphinx.c(152): Parsed model-specific feature parameters from zh_broadcastnews_16k_ptm256_8000/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                    live            current
-cmninit                40,3,-1         40,3,-1
-compallsen             no              no
-debug                                  0
-dict                                   a.dic
-dictcase               no              no
-dither                 no              no
-doublebw               no              no
-ds                     1               1
-fdict
-feat                   1s_c_d_dd       s2_4x
-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