pocketsphinx-android

I have did a lot for research and tried offline pocket sphinx but it is taking surrounding voice it is taking and reacting my app differently. Is there any Google offline app for above kitkat 4.4.. i am trying it from 2 week. Thank for your valuable answer. Details: When the activity starts first text has to read the content (Text to speech) after it complete, reading voice recognition has to take voice and as per command ex: (next, previous, forward, option, 1, 2, 3, 4 etc). As per command it has to recognize and react to it in onresult method. Error: i am getting error after taking some

I am using the latest pocketsphinx android demo (mighty computer),which takes input from microphone. I want to give a wav file as input to the same. I tried using decoder.processrow() function. But I don't know how to configure the decoder using hmm, lm etc. Code to process files in pocketsphinx-java Config c = Decoder.defaultConfig(); c.setString("-hmm", "../../model/en-us/en-us"); c.setString("-lm", "../../model/en-us/en-us.lm.dmp"); c.setString("-dict", "../../model/en-us/cmudict-en-us.dict"); Decoder d = new Decoder(c); URL testwav = new URL("file:../../test/data/goforward.wav");

I downloaded the source code of pocket sphinx demo. I'm trying to run it but it is throwing a runtime exception. I've posted the logcat of my code. 09-09 11:45:38.980: I/System.out(7912): Sending WAIT chunk 09-09 11:45:38.980: W/ActivityThread(7912): Application edu.cmu.pocketsphinx.demo is waiting for the debugger on port 8100... 09-09 11:45:39.030: I/dalvikvm(7912): Debugger is active 09-09 11:45:39.210: I/System.out(7912): Debugger has connected 09-09 11:45:39.210: I/System.out(7912): waiting for debugger to settle... 09-09 11:45:39.400: I/System.out(7912): waiting for debugger to settle...

Before I tried to used PocketSphinx for Android, I used Google's voice recognition API. I didn't need to set a search name or a dictionary file. It just recognized every word that was told. Now, In PocketSphinx, I need to do it. But I can only find how to set recognition for one word, Or to set dictionary (The ones available in the demo project have only few words) that the recognizer think these are the only words exist, Which means that if someone says something similar, The recognizer thinks its the word that listed in the dictionary. I just want to ask, How could I set a few search names,