Voice Recognition Implementation

[Naveen_D]

@mrjj thanks, how to use this existing examples in pocketsphinx ?

[mrjj]

@Naveen_D said in Voice Recognition Implementation:

pocketsphinx

http://cmusphinx.sourceforge.net/wiki/tutorialpocketsphinx

There is a Basic Usage (hello world) sample.
That should do it :)

[Naveen_D]

@mrjj Do i need to install sphinx train also for this ????

[Naveen_D]

@mrjj hi,

When run this command

pocketsphinx_continuous
-hmm /usr/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k
-dict /usr/share/pocketsphinx/model/lm/en_US/cmu07a.dic
-lm /usr/share/pocketsphinx/model/lm/en_US/hub4.5000.DMP

i get this output can u pls tell me wats the prb here...
INFO: continuous.c(295): Specify '-infile <file.wav>' to recognize from file or '-inmic yes' to recognize from microphone.

[Naveen_D]

Also i am not able to understand what they are doing in the hello world example in
http://cmusphinx.sourceforge.net/wiki/tutorialpocketsphinx can anyone pls help me out in this concern

[mrjj]

@Naveen_D said in Voice Recognition Implementation:

INFO: continuous.c(295): Specify '-infile <file.wav>' to recognize from file or '-inmic yes' to recognize from microphone.

Sadly I dont know pocketsphinx, i just browsed over the docs to help you,

if I should guess, i think it ask where to get the input from.
You give it the data files ( dic + friends) and then it says
give me -INFILE for a file with input or -inmic to use your mic.

• Also i am not able to understand what they are doing in the hello world example
  Which part? There are pretty good explaining in between the code.
  Not sure we can make it much better unless some user comes by that
  actually use pocketsphinx :)

[Naveen_D]

Is there any other open source api which i can use for voice recognition in qt??

[mrjj]

@Naveen_D
Hi, you can try the QtSpeech as SGaist mentions.
It seems it uses pocket also
http://cmusphinx.sourceforge.net/2015/10/qtspeechrecognition-api-for-qt-using-pocketsphinx/
"You can find the sources in review in qtspeech project, branch wip/speech-recognition."

So maybe :)

[Naveen_D]

@mrjj hi yes i will try with that also thanks
QtSpeech is it for text to speech or speech to text ?

[mrjj]

@Naveen_D
HI
As the Champ says:

"Hi, Just in case, there's a speech recognition branch in the QtSpeech "

[Naveen_D]

@mrjj okay i will try it thanks

[mrjj]

@Naveen_D
Good luck :)

[Naveen_D]

@mrjj Hi i am trying voice recognition with julius, I have installed julius on my ubuntu system and configured it, i have created one my.jconfg file from the sample.jconfg file which i got after installing julius. but when i run that, I get the following output

ubuntu@ub:~/Documents/julius-4.2.2/test$ padsp julius -C my.jconf
STAT: include config: my.jconf

<<< please speak >>>^C

I am not sure is it running or not, How to confirm that it is running or not ?

[jsulm]

@Naveen_D To me it looks like it is running and asking you to say something :-)
If you have a microphone connected you should try to say something - this is a speech recognition system at the end :-)

[mrjj]

Hi
As @jsulm says , it does seem to be running :)
You might need -iput mic unless its default
padsp julius -iput mic -C julian.conf.

[Naveen_D]

Thanks...it works fine for that example

[mrjj]

@Naveen_D
\o/
Finally !

[Naveen_D]

@mrjj But one problem is there...when i change the .grammar and .voca files for different commands it gives error i followed the steps given in this link http://www.voxforge.org/home/dev/acousticmodels/linux/create/htkjulius/tutorial/data-prep/step-1 to generate .grammar and .voca files and generate their respective .dict and .dfa files but when i run it gives, error in loading model...it only worked for the test example which was provided in that link.... :-(

When i run the command after changing that files this is the output...

ubuntu@ub:~/Documents/julius-4.2.2/SampleTest$ padsp julius -C my.jconfSTAT: include config: my.jconf
ERROR: Error in loading model
ubuntu@ub:~/Documents/julius-4.2.2/SampleTest$ ^C

[Naveen_D]

Sorry i got the test example from the following link...
http://kamilskowron.pl/en/linux/julius-step-by-step-step-2-basic-configuration/

[mrjj]

@Naveen_D

Hi So it will generate the .dict etc for the sample , but if you try with your own files it wont?
Did you try his next sample with the media player as reference ?