Speech recognization from .wav file using pocketsphinx_continuous.exe

[abdul haseeb]

Hi all,
i have written a code in c# to recognize speech from .wav file. My code could successfully recognize all digits except "six". And the dict i am using consist

zero        Z IH R OW
zero(2)     Z IY R OW
zero(3)     DH UW D V V IY R AE
zero(4)     DH UW DH V DH IY N ER AH AW AH L
one         W AH N
one(2)      HH W AH N
two         T UW
two(2)      D CH UH M
three       TH R IY
three(2)    T DH EY L IY IY
three(3)    D EY L IY EY IY IY
four        F AO R
four(2)     DH AH L AO AH N
five        F AY V
six         S IH K S
six(1)      S F IH K S
six(2)      DH EY T D HH DH G
six(3)      DH EY P HH DH G
seven       S EH V AH N
eight       EY T
eight(2)    DH AH EY IY
nine        N AY N

and the language model i am using is

This is an ARPA-format language model file, generated by CMU Sphinx
\data\
ngram 1=12

\1-grams:
-1.4016 </s> -0.4051
-99.0000 <s> 1.4124
-3.8842 zero -0.4376
-2.4976 one -0.4239
-2.7508 two -0.2802
-2.9571 three -0.3222
-3.0738 four -0.3780
-2.9962 five -0.4140
-3.1903 six -0.3997
-3.2768 seven -0.3833
-3.3046 eight -0.3988
-3.4077 nine -0.3758

\end\

and my command line is
Arguments = "/c pocketsphinx_continuous.exe -infile cccccc_converted.wav -hmm Bunch -lm en-us.lm -dict micro.dict"

Please help me to resolve this issue or mail me the correct dict or lm to my mail id mabdulhaseeb44@gmail.com

Thanks in Advance.

waiting for u suggestions and reply........

[Nickolay V. Shmyrev]

To get help on accuracy you need to provide an audio data to reproduce your problems.