Handling Errors in PocketSphinx Android app

Handling Errors in PocketSphinx Android app - android

I am using the default dictionary that comes with the pocketsphinx demo which is good for my purposes. When a user enters a phrase, the app starts a keyphrase listening but if the word is not found in the dictionary the app crashes. The app crashes onError() within a service. How is the error handling done? is there any way I can catch the error? Overall I would just like the service to call stopSelf() when an error happens so the main activity won't crash as well.
Errors:
ERROR: "kws_search.c", line 165: The word 'phonez' is missing in the dictionary
Fatal signal 11 (SIGSEGV) at 0x00000000 (code=1), thread 5389 (1994.wherephone)
Here is my service class:
public class WherePhoneService extends Service implements RecognitionListener {
private static String SettingStorage = "SavedData";
SharedPreferences settingData;
private SpeechRecognizer recognizer;
private String sInput;
private String sOutput;
private int seekVal;
private TextToSpeech reply;
private AsyncTask t;
public WherePhoneService() {
}
#Override
public IBinder onBind(Intent intent) {
// TODO: Return the communication channel to the service.
throw new UnsupportedOperationException("Not yet implemented");
}
#Override
public int onStartCommand(Intent intent, int flags, int startId) {
makeText(getApplicationContext(), "onHandle start", Toast.LENGTH_SHORT).show();
getValues();
startTTS();
t = new AsyncTask<Void, Void, Exception>() {
#Override
protected Exception doInBackground(Void... params) {
try {
Assets assets = new Assets(WherePhoneService.this);
File assetDir = assets.syncAssets();
setupRecognizer(assetDir);
} catch (IOException e) {
return e;
}
return null;
}
#Override
protected void onPostExecute(Exception result) {
if (result != null) {
//((TextView) findViewById(R.id.caption_text)).setText("Failed to init recognizer " + result);
} else {
switchSearch(sInput);
}
}
}.execute();
return Service.START_STICKY;
}
private void setupRecognizer(File assetsDir) throws IOException {
recognizer = defaultSetup()
.setAcousticModel(new File(assetsDir, "en-us-ptm"))
.setDictionary(new File(assetsDir, "cmudict-en-us.dict"))
// To disable logging of raw audio comment out this call (takes a lot of space on the device)
//.setRawLogDir(assetsDir)
// Threshold to tune for keyphrase to balance between false alarms and misses
.setKeywordThreshold(1e-45f)
// Use context-independent phonetic search, context-dependent is too slow for mobile
.setBoolean("-allphone_ci", true)
.getRecognizer();
recognizer.addListener(this);
// Create keyword-activation search.
recognizer.addKeyphraseSearch(sInput, sInput);
}
private void switchSearch(String searchName) {
recognizer.stop();
// If we are not spotting, start listening with timeout (10000 ms or 10 seconds).
if (searchName.equals(sInput))
recognizer.startListening(searchName);
else
recognizer.startListening(searchName, 10000);
}
#Override
public void onBeginningOfSpeech() {
}
#Override
public void onEndOfSpeech() {
if (!recognizer.getSearchName().equals(sInput))
switchSearch(sInput);
}
#Override
public void onPartialResult(Hypothesis hypothesis) {
if (hypothesis == null)
return;
String text = hypothesis.getHypstr();
makeText(getApplicationContext(), "Partial", Toast.LENGTH_SHORT).show();
if (text.equals(sInput)) {
setVolume();
// Text to speech
reply.speak(sOutput, TextToSpeech.QUEUE_ADD, null);
switchSearch(sInput);
}
else {
makeText(getApplicationContext(), "Try again", Toast.LENGTH_SHORT).show();
switchSearch(sInput);
}
}
#Override
public void onResult(Hypothesis hypothesis) {
if (hypothesis != null) {
// restart listener and affirm that partial has past
makeText(getApplicationContext(), "end", Toast.LENGTH_SHORT).show();
//recognizer.startListening(sInput);
switchSearch(sInput);
}
}
public void onError(Exception e) {
e.printStackTrace(); // not all Android versions will print the stack trace automatically
Intent intent = new Intent ();
intent.setAction ("com.mydomain.SEND_LOG"); // see step 5.
intent.setFlags (Intent.FLAG_ACTIVITY_NEW_TASK); // required when starting from Application
startActivity (intent);
stopSelf();
}
#Override
public void onTimeout() {
switchSearch(sInput);
}
public void startTTS() {
reply = new TextToSpeech(getApplicationContext(), new TextToSpeech.OnInitListener() {
#Override
public void onInit(int status) {
if(status != TextToSpeech.ERROR){
reply.setLanguage(Locale.UK);
}
}
});
}
public void getValues() {
settingData = getBaseContext().getSharedPreferences(SettingStorage, 0);
sInput = settingData.getString("inputstring", "Where is my phone").toString().toLowerCase().replaceAll("[^\\w\\s]", "");
sOutput = settingData.getString("outputstring", "").toString().toLowerCase();
seekVal = settingData.getInt("seekval", 0);
}
public void setVolume() {
int seekValConvert = 0;
AudioManager audioManager = (AudioManager) getSystemService(Context.AUDIO_SERVICE);
int getMaxPhoneVol = audioManager.getStreamMaxVolume(audioManager.STREAM_MUSIC);
seekValConvert = ((seekVal * getMaxPhoneVol)/100);
audioManager.setStreamVolume(audioManager.STREAM_MUSIC, seekValConvert, 0);
}
#Override
public void onDestroy() {
super.onDestroy();
makeText(getApplicationContext(), "destroy", Toast.LENGTH_SHORT).show();
recognizer.cancel();
recognizer.shutdown();
t.cancel(true);
}
}

Crash is a bug in pocketsphinx-android. If you update to latest version from github, it should properly throw RuntimeException on any errors in methods addKeyphrase and setSearch.

Related

PocketSphinx on Android recognises words even if they aren't spoken

I am using PocketSphinx for android-23.
I want to code an offline assistant for one of my apps.
I have successfully used recognizer.addKeyphraseSearch to initialize the assistant. For eg. In this case I say "Hello" to initialize it.
this is my entire code
public class Farmax_2 extends Activity implements
RecognitionListener {
/* Named searches allow to quickly reconfigure the decoder */
private static final String KWS_SEARCH = "wakeup";
private static final String ahead = "about";
private static final String PHONE_SEARCH = "ahead";
private static final String MENU_SEARCH = "menu";
TextToSpeech t1;
Button btn;
/* Keyword we are looking for to activate menu */
private static final String KEYPHRASE = "hello";
/* Used to handle permission request */
private static final int PERMISSIONS_REQUEST_RECORD_AUDIO = 1;
private SpeechRecognizer recognizer;
private HashMap<String, Integer> captions;
#Override
public void onCreate(Bundle state) {
super.onCreate(state);
setContentView(R.layout.activity_farmax_2);
// Check if user has given permission to record audio
int permissionCheck = ContextCompat.checkSelfPermission(getApplicationContext(), Manifest.permission.RECORD_AUDIO);
if (permissionCheck != PackageManager.PERMISSION_GRANTED) {
ActivityCompat.requestPermissions(this, new String[]{Manifest.permission.RECORD_AUDIO}, PERMISSIONS_REQUEST_RECORD_AUDIO);
return;
}
btn=(Button)findViewById(R.id.buttonme);
btn.setOnClickListener(new View.OnClickListener() {
#Override
public void onClick(View v) {
Intent inte = new Intent(Farmax_2.this, MainMenu.class);
startActivity(inte);
}
});
t1 = new TextToSpeech(getApplicationContext(), new TextToSpeech.OnInitListener() {
#Override
public void onInit(int status) {
if (status != TextToSpeech.ERROR) {
t1.setLanguage(Locale.UK);
}
}
});
runRecognizerSetup();
}
public void omku(View view) { Intent in=new Intent(this,abtus.class);
startActivity(in);}
private void runRecognizerSetup() {
// Recognizer initialization is a time-consuming and it involves IO,
// so we execute it in async task
new AsyncTask<Void, Void, Exception>() {
#Override
protected Exception doInBackground(Void... params) {
try {
Assets assets = new Assets(Farmax_2.this);
File assetDir = assets.syncAssets();
setupRecognizer(assetDir);
} catch (IOException e) {
return e;
}
return null;
}
#Override
protected void onPostExecute(Exception result) {
if (result != null) {
} else {
switchSearch(KWS_SEARCH);
}
}
}.execute();
}
#Override
public void onRequestPermissionsResult(int requestCode,
String[] permissions, int[] grantResults) {
super.onRequestPermissionsResult(requestCode, permissions, grantResults);
if (requestCode == PERMISSIONS_REQUEST_RECORD_AUDIO) {
if (grantResults.length > 0 && grantResults[0] == PackageManager.PERMISSION_GRANTED) {
runRecognizerSetup();
} else {
finish();
}
}
}
#Override
public void onDestroy() {
super.onDestroy();
if (recognizer != null) {
recognizer.cancel();
recognizer.shutdown();
}
}
/**
* In partial result we get quick updates about current hypothesis. In
* keyword spotting mode we can react here, in other modes we need to wait
* for final result in onResult.
*/
#Override
public void onPartialResult(Hypothesis hypothesis) {
if (hypothesis == null)
return;
String text = hypothesis.getHypstr();
switch (text) {
case KEYPHRASE: {
omkar();
break;
}
case ahead: {
Intent in = new Intent(this, abtus.class);
startActivity(in);
break;
// t1.speak("taking you to privacy policy of farmax.", TextToSpeech.QUEUE_FLUSH, null);
}
case PHONE_SEARCH: {
Intent in = new Intent(this, MainMenu.class);
startActivity(in);
// t1.speak("Main Menu.", TextToSpeech.QUEUE_FLUSH, null);
break;
}
}
}
private void omkar() {
t1.speak("Yes sir.", TextToSpeech.QUEUE_FLUSH, null);
switchSearch(MENU_SEARCH);
}
/**
* This callback is called when we stop the recognizer.
*/
#Override
public void onResult(Hypothesis hypothesis) {
if (hypothesis != null) {
String text = hypothesis.getHypstr();
makeText(getApplicationContext(), text, Toast.LENGTH_SHORT).show();
}
}
#Override
public void onBeginningOfSpeech() {
}
/**
* We stop recognizer here to get a final result
*/
#Override
public void onEndOfSpeech() {
}
private void switchSearch(String searchName) {
recognizer.stop();
// If we are not spotting, start listening with timeout (10000 ms or 10 seconds).
if (searchName.equals(KWS_SEARCH))
recognizer.startListening(searchName);
else
recognizer.startListening(searchName, 10000);
}
private void setupRecognizer(File assetsDir) throws IOException {
// The recognizer can be configured to perform multiple searches
// of different kind and switch between them
recognizer = SpeechRecognizerSetup.defaultSetup()
.setAcousticModel(new File(assetsDir, "en-us-ptm"))
.setDictionary(new File(assetsDir, "cmudict-en-us.dict"))
.setRawLogDir(assetsDir) // To disable logging of raw audio comment out this call (takes a lot of space on the device)
.getRecognizer();
recognizer.addListener(this);
/** In your application you might not need to add all those searches.
* They are added here for demonstration. You can leave just one.
*/
// Create keyword-activation search.
recognizer.addKeyphraseSearch(KWS_SEARCH, "hello");
// Create grammar-based search for selection between demos
File menuGrammar = new File(assetsDir, "firstscn.gram");
recognizer.addGrammarSearch(MENU_SEARCH, menuGrammar);
// Create grammar-based search for digit recognition
}
#Override
public void onError(Exception error) {
}
#Override
public void onTimeout() {
switchSearch(KWS_SEARCH);
}
}
when I say hello, it responds correctly by replying "Yes sir" via tts. But after that it is supposed to switch menu and wait for the further commands. In this case there are two.
#Override
public void onPartialResult(Hypothesis hypothesis) {
if (hypothesis == null)
return;
String text = hypothesis.getHypstr();
switch (text) {
case KEYPHRASE: {
omkar();
break;
}
case ahead: {
Intent in = new Intent(this, abtus.class);
startActivity(in);
break;
// t1.speak("taking you to privacy policy of farmax.", TextToSpeech.QUEUE_FLUSH, null);
}
case PHONE_SEARCH: {
Intent in = new Intent(this, MainMenu.class);
startActivity(in);
// t1.speak("Main Menu.", TextToSpeech.QUEUE_FLUSH, null);
break;
}
}
}
But the problem is that It doesnt wait for my command after it switches the menu.
Sometimes a toast pops up with "about" or sometimes with "ahead" even though I dont speak them. The app freezes badly after that and leaves me no other option than to close it.
If have also tried if else statements other than switch and case. But they don't seem to help much.
I have also tried to use the above code in onResult rather than onPartialResult but that doesnt help as well.
using sphinx tools I have created my own dictionary and grammar file.
Here is the grammar file content for this case.
#JSGF V1.0;
grammar firstscn;
public <item> = about | ahead;
Where am I going wrong? Please help me.

Loop SpeechRecognizer in Android [duplicate]

I have managed to get continuous speech recognition working (using the SpeechRecognizer class) as a service on all Android versions up to 4.1. My question concerns getting it working on versions 4.1 and 4.2 as it is known there is a problem in that the API doesn't do as documented in that a few seconds after voice recognition is started, if no voice input has been detected then it's as if the speech recogniser dies silently. (http://code.google.com/p/android/issues/detail?id=37883)
I have found a question which proposes a work-around to this problem (Voice Recognition stops listening after a few seconds), but I am unsure as how to implement the Handler required for this solution. I am aware of the 'beep' that will happen every few seconds that this workaround will cause, but getting continuous voice recognition is more important for me.
If anyone has any other alternative workarounds then I'd like to hear those too.

This is a work around for android version 4.1.1.
public class MyService extends Service
{
protected AudioManager mAudioManager;
protected SpeechRecognizer mSpeechRecognizer;
protected Intent mSpeechRecognizerIntent;
protected final Messenger mServerMessenger = new Messenger(new IncomingHandler(this));
protected boolean mIsListening;
protected volatile boolean mIsCountDownOn;
private boolean mIsStreamSolo;
static final int MSG_RECOGNIZER_START_LISTENING = 1;
static final int MSG_RECOGNIZER_CANCEL = 2;
#Override
public void onCreate()
{
super.onCreate();
mAudioManager = (AudioManager) getSystemService(Context.AUDIO_SERVICE);
mSpeechRecognizer = SpeechRecognizer.createSpeechRecognizer(this);
mSpeechRecognizer.setRecognitionListener(new SpeechRecognitionListener());
mSpeechRecognizerIntent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
mSpeechRecognizerIntent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL,
RecognizerIntent.LANGUAGE_MODEL_FREE_FORM);
mSpeechRecognizerIntent.putExtra(RecognizerIntent.EXTRA_CALLING_PACKAGE,
this.getPackageName());
}
protected static class IncomingHandler extends Handler
{
private WeakReference<MyService> mtarget;
IncomingHandler(MyService target)
{
mtarget = new WeakReference<MyService>(target);
}
#Override
public void handleMessage(Message msg)
{
final MyService target = mtarget.get();
switch (msg.what)
{
case MSG_RECOGNIZER_START_LISTENING:
if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.JELLY_BEAN)
{
// turn off beep sound
if (!mIsStreamSolo)
{
mAudioManager.setStreamSolo(AudioManager.STREAM_VOICE_CALL, true);
mIsStreamSolo = true;
}
}
if (!target.mIsListening)
{
target.mSpeechRecognizer.startListening(target.mSpeechRecognizerIntent);
target.mIsListening = true;
//Log.d(TAG, "message start listening"); //$NON-NLS-1$
}
break;
case MSG_RECOGNIZER_CANCEL:
if (mIsStreamSolo)
{
mAudioManager.setStreamSolo(AudioManager.STREAM_VOICE_CALL, false);
mIsStreamSolo = false;
}
target.mSpeechRecognizer.cancel();
target.mIsListening = false;
//Log.d(TAG, "message canceled recognizer"); //$NON-NLS-1$
break;
}
}
}
// Count down timer for Jelly Bean work around
protected CountDownTimer mNoSpeechCountDown = new CountDownTimer(5000, 5000)
{
#Override
public void onTick(long millisUntilFinished)
{
// TODO Auto-generated method stub
}
#Override
public void onFinish()
{
mIsCountDownOn = false;
Message message = Message.obtain(null, MSG_RECOGNIZER_CANCEL);
try
{
mServerMessenger.send(message);
message = Message.obtain(null, MSG_RECOGNIZER_START_LISTENING);
mServerMessenger.send(message);
}
catch (RemoteException e)
{
}
}
};
#Override
public void onDestroy()
{
super.onDestroy();
if (mIsCountDownOn)
{
mNoSpeechCountDown.cancel();
}
if (mSpeechRecognizer != null)
{
mSpeechRecognizer.destroy();
}
}
protected class SpeechRecognitionListener implements RecognitionListener
{
#Override
public void onBeginningOfSpeech()
{
// speech input will be processed, so there is no need for count down anymore
if (mIsCountDownOn)
{
mIsCountDownOn = false;
mNoSpeechCountDown.cancel();
}
//Log.d(TAG, "onBeginingOfSpeech"); //$NON-NLS-1$
}
#Override
public void onBufferReceived(byte[] buffer)
{
}
#Override
public void onEndOfSpeech()
{
//Log.d(TAG, "onEndOfSpeech"); //$NON-NLS-1$
}
#Override
public void onError(int error)
{
if (mIsCountDownOn)
{
mIsCountDownOn = false;
mNoSpeechCountDown.cancel();
}
mIsListening = false;
Message message = Message.obtain(null, MSG_RECOGNIZER_START_LISTENING);
try
{
mServerMessenger.send(message);
}
catch (RemoteException e)
{
}
//Log.d(TAG, "error = " + error); //$NON-NLS-1$
}
#Override
public void onEvent(int eventType, Bundle params)
{
}
#Override
public void onPartialResults(Bundle partialResults)
{
}
#Override
public void onReadyForSpeech(Bundle params)
{
if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.JELLY_BEAN)
{
mIsCountDownOn = true;
mNoSpeechCountDown.start();
}
Log.d(TAG, "onReadyForSpeech"); //$NON-NLS-1$
}
#Override
public void onResults(Bundle results)
{
//Log.d(TAG, "onResults"); //$NON-NLS-1$
}
#Override
public void onRmsChanged(float rmsdB)
{
}
}
}
02/16/2013 - Fix beep sound if you use Text To Speech in your app make sure to turn off Solo stream in onResults

If you really want to implement continuous listening without internet connection you need to consider third-party packages, one of them is CMUSphinx, check Pocketsphinx android demo for example how to listen for keyword efficiently in offline and react on the specific commands like a key phrase "oh mighty computer". The code to do that is simple:
you create a recognizer and just add keyword spotting search:
recognizer = defaultSetup()
.setAcousticModel(new File(modelsDir, "hmm/en-us-semi"))
.setDictionary(new File(modelsDir, "lm/cmu07a.dic"))
.setKeywordThreshold(1e-5f)
.getRecognizer();
recognizer.addListener(this);
recognizer.addKeywordSearch(KWS_SEARCH_NAME, KEYPHRASE);
switchSearch(KWS_SEARCH_NAME);
and define a listener:
#Override
public void onPartialResult(Hypothesis hypothesis) {
String text = hypothesis.getHypstr();
if (text.equals(KEYPHRASE))
// do something
}

For any of you who are trying to silence the beep sound, regrading the #HoanNguyen answer which is very good but be careful as said in the api set setStreamSolo is cumulative so if there is in error in the speech recognition and on error is called(for example no internet connection) then setStremSolo true is called again and again which will result in your app silencing the whole phone (very bad)! the solution to that is to add the setStremMute(false) to the speechRecognizer onError.

check out my demo app :
https://github.com/galrom/ContinuesVoiceRecognition
I recommand to use both PockeySphix and SpeechRecognizer.

Speech recognizer: not connected to the recognition service error after onPause

Hi I'm implementing continuous speech listening in my application, but when i destroy the speech recognizer in onPause i get not connected to the recognition service error.
I already read this question, and the relative answer, but it doesn't seem to solve the problem.
This is the code that generates the error:
// Activity code
#Override
public void onPause()
{
assistant.dismiss();
super.onPause();
}
#Override
public void onResume()
{
super.onResume();
assistant = new Assistant(this);
Log.d(TAG,"resume");
}
Assistant code:
public class Assistant extends UtteranceProgressListener implements RecognitionListener, TextToSpeech.OnInitListener
{
private static final String TAG = "Assistant" ;
private Context context ;
private Intent intent ;
private SpeechRecognizer speechRecognizer;
private TextToSpeech textToSpeech;
private static AudioManager audioManager;
private boolean isAudioMute;
String actionAnswer ;
public Assistant ( Context context )
{
this.context = context;
isAudioMute = false ;
textToSpeech = new TextToSpeech(context, this);
textToSpeech.setOnUtteranceProgressListener(this);
if ( SpeechRecognizer.isRecognitionAvailable(context))
{
intent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
intent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL,
RecognizerIntent.LANGUAGE_MODEL_FREE_FORM);
intent.putExtra(RecognizerIntent.EXTRA_CALLING_PACKAGE,
context.getPackageName());
speechRecognizer = SpeechRecognizer.createSpeechRecognizer(context);
speechRecognizer.setRecognitionListener(this);
audioManager = (AudioManager) context.getSystemService(Context.AUDIO_SERVICE);
}
else
{
Log.e(TAG, "speech recognizer not avaiable");
}
}
private void startListening()
{
if ( !isAudioMute )
{
audioManager.setStreamMute(AudioManager.STREAM_MUSIC, true);
isAudioMute = true ;
}
((Activity)context).runOnUiThread(new Runnable()
{
#Override
public void run()
{
speechRecognizer.startListening(intent);
Log.d(TAG, "startlisten");
}
});
}
private void stopListening()
{
speechRecognizer.stopListening();
try
{
// wait for annoying sound to happens, then unmute channel.
Thread.sleep(400);
}
catch (InterruptedException e)
{
e.printStackTrace();
}
Log.d(TAG, "stoplistne");
if ( isAudioMute )
{
audioManager.setStreamMute(AudioManager.STREAM_MUSIC, false);
isAudioMute = false ;
}
}
public void dismiss()
{
((Activity)context).runOnUiThread(new Runnable()
{
#Override
public void run()
{
speechRecognizer.stopListening();
speechRecognizer.cancel();
speechRecognizer.destroy();
speechRecognizer = null;
}
});
try
{
// wait for annoying sound to happens, then unmute channel.
Thread.sleep(400);
}
catch (InterruptedException e)
{
e.printStackTrace();
}
Log.d(TAG, "stoplistne");
if ( isAudioMute )
{
audioManager.setStreamMute(AudioManager.STREAM_MUSIC, false);
isAudioMute = false ;
}
textToSpeech.stop();
textToSpeech.shutdown();
textToSpeech = null;
}
private void speakOut(String text)
{
stopListening();
if (Build.VERSION.SDK_INT >= 21 )
{
if (textToSpeech.speak(text, TextToSpeech.QUEUE_FLUSH, null, this.getClass().getName()) != TextToSpeech.SUCCESS)
Log.e(TAG, "failed to queue text " + text);
}
else
{
if (textToSpeech.speak(text.toString(), TextToSpeech.QUEUE_FLUSH, null) != TextToSpeech.SUCCESS)
Log.e(TAG, "failed to queue text " + text);
}
}
// text to speech
#Override
public void onInit(int status)
{
if (status == TextToSpeech.SUCCESS)
{
int result = textToSpeech.setLanguage(Locale.US);
if (result == TextToSpeech.LANG_MISSING_DATA
|| result == TextToSpeech.LANG_NOT_SUPPORTED)
{
Log.e(TAG, "This Language is not supported");
return;
}
speakOut("Assistant Ready");
}
else
{
Log.e(TAG, "Initilization Failed!");
}
}
// SpeechRecognizer
#Override
public void onReadyForSpeech(Bundle params)
{
Log.d(TAG, "readyforspeech");
}
// SpeechRecognizer
#Override
public void onBeginningOfSpeech()
{
Log.d(TAG, "beginningofspeech");
}
// SpeechRecognizer
#Override
public void onRmsChanged(float rmsdB)
{
}
// SpeechRecognizer
#Override
public void onBufferReceived(byte[] buffer)
{
Log.d(TAG, "bufferreceived");
}
// SpeechRecognizer
#Override
public void onEndOfSpeech()
{
Log.d(TAG, "endofspeech");
}
// SpeechRecognizer
#Override
public void onError(int error)
{
Log.d("SPEECH", "onError: " + error);
switch(error)
{
case SpeechRecognizer.ERROR_AUDIO:
Log.d(TAG,"ERROR_AUDIO");
break;
case SpeechRecognizer.ERROR_CLIENT:
Log.d(TAG,"ERROR_CLIENT");
break;
case SpeechRecognizer.ERROR_INSUFFICIENT_PERMISSIONS:
Log.d(TAG,"ERROR_INSUFFICIENT_PERMISSIONS");
break;
case SpeechRecognizer.ERROR_NETWORK:
Log.d(TAG,"ERROR_NETWORK");
break;
case SpeechRecognizer.ERROR_NETWORK_TIMEOUT:
Log.d(TAG,"ERROR_NETWORK_TIMEOUT");
break;
case SpeechRecognizer.ERROR_NO_MATCH:
Log.d(TAG,"ERROR_NO_MATCH");
startListening();
break;
case SpeechRecognizer.ERROR_RECOGNIZER_BUSY:
Log.d(TAG,"ERROR_RECOGNIZER_BUSY");
break;
case SpeechRecognizer.ERROR_SERVER:
Log.d(TAG,"ERROR_SERVER");
break;
case SpeechRecognizer.ERROR_SPEECH_TIMEOUT:
Log.d(TAG,"ERROR_SPEECH_TIMEOUT");
startListening();
break;
default:
Log.d(TAG,"ERROR_UNKNOWN");
}
}
// SpeechRecognizer
#Override
public void onResults(Bundle results)
{
ArrayList<String> res = results. getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION) ;
Log.i(TAG,"res: '" + res.get(0) +"'.");
actionAnswer = res.get(0);
speakOut(actionAnswer);
}
// SpeechRecognizer
#Override
public void onPartialResults(Bundle partialResults)
{
}
// SpeechRecognizer
#Override
public void onEvent(int eventType, Bundle params)
{
}
// Utterance progress listener
#Override
public void onStart(String utteranceId)
{
Log.d(TAG, "onstart");
}
// Utterance progress listener
#Override
public void onDone(String utteranceId)
{
Log.d(TAG, "ondone");
startListening();
}
// Utterance progress listener
#Override
public void onError(String utteranceId)
{
Log.d(TAG, "onerror");
}
}
Anyway, even if the error occurs, when i reinitialize the speech recognizer everything works fine, so i'm not sure if i have to worry about the error.

Don't use speechRecognizer.stopListening() and speechRecognizer.cancel(),
Use speechRecognizer.destroy() instead.

Getting speech to text Android

I have been refering to Android Speech Recognition as a service on Android 4.1 & 4.2 post to try and implement speech recognition in a service.
I guess I have got it right. On running in my device I am getting "Ready for Speech" toast message which I have declared inside onReadyForSpeech() function.
According to Hoan Nguyen the person who gave the ans for the above post, we can start speaking as soon as onReadyForSpeech() function is called.
My problem is I don't know how to get the speech which we are speaking and convert it to text and where to do it.
Does any one know how to do it? I know its a very lame question to ask but its my first time working with speech recognition. So please bear with me.
Any help on this is very much appreciated. Thanks in advance :)
public class MyService extends Service
{
protected AudioManager mAudioManager;
protected SpeechRecognizer mSpeechRecognizer;
protected Intent mSpeechRecognizerIntent;
protected final Messenger mServerMessenger = new Messenger(new IncomingHandler(this));
protected boolean mIsListening;
protected volatile boolean mIsCountDownOn;
static final int MSG_RECOGNIZER_START_LISTENING = 1;
static final int MSG_RECOGNIZER_CANCEL = 2;
#Override
public void onCreate()
{
super.onCreate();
mAudioManager = (AudioManager) getSystemService(Context.AUDIO_SERVICE);
mSpeechRecognizer = SpeechRecognizer.createSpeechRecognizer(this);
mSpeechRecognizer.setRecognitionListener(new SpeechRecognitionListener());
mSpeechRecognizerIntent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
mSpeechRecognizerIntent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL,
RecognizerIntent.LANGUAGE_MODEL_FREE_FORM);
mSpeechRecognizerIntent.putExtra(RecognizerIntent.EXTRA_CALLING_PACKAGE,
this.getPackageName());
mSpeechRecognizer.startListening(mSpeechRecognizerIntent);
//Toast.makeText(this, "onCreate", Toast.LENGTH_SHORT).show();
Log.d("onCreate","Entered");
}
protected static class IncomingHandler extends Handler
{
private WeakReference<MyService> mtarget;
IncomingHandler(MyService target)
{
mtarget = new WeakReference<MyService>(target);
Log.d("IncomingHandler","Entered");
}
#Override
public void handleMessage(Message msg)
{
Log.d("handleMessage","Entered");
final MyService target = mtarget.get();
switch (msg.what)
{
case MSG_RECOGNIZER_START_LISTENING:
if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.JELLY_BEAN)
{
// turn off beep sound
target.mAudioManager.setStreamMute(AudioManager.STREAM_SYSTEM, true);
}
if (!target.mIsListening)
{
target.mSpeechRecognizer.startListening(target.mSpeechRecognizerIntent);
target.mIsListening = true;
Log.d("TAG", "message start listening");
//$NON-NLS-1$
}
break;
case MSG_RECOGNIZER_CANCEL:
target.mSpeechRecognizer.cancel();
target.mIsListening = false;
Log.d("TAG", "message canceled recognizer"); //$NON-NLS-1$
break;
}
}
}
// Count down timer for Jelly Bean work around
protected CountDownTimer mNoSpeechCountDown = new CountDownTimer(5000, 5000)
{
#Override
public void onTick(long millisUntilFinished)
{
// TODO Auto-generated method stub
Log.d("onTick","Entered");
}
#Override
public void onFinish()
{
Log.d("onFinish","Entered");
mIsCountDownOn = false;
Message message = Message.obtain(null, MSG_RECOGNIZER_CANCEL);
try
{
mServerMessenger.send(message);
message = Message.obtain(null, MSG_RECOGNIZER_START_LISTENING);
mServerMessenger.send(message);
}
catch (RemoteException e)
{
}
}
};
#Override
public int onStartCommand(Intent intent, int flags, int startId) {
// TODO Auto-generated method stub
//mSpeechRecognizer.startListening(mSpeechRecognizerIntent);
try
{
Message msg = new Message();
msg.what = MSG_RECOGNIZER_START_LISTENING;
mServerMessenger.send(msg);
}
catch (RemoteException e)
{
Log.d("msg",""+e);
}
return START_NOT_STICKY;
//return super.onStartCommand(intent, flags, startId);
}
#Override
public void onDestroy()
{
super.onDestroy();
if (mIsCountDownOn)
{
mNoSpeechCountDown.cancel();
}
if (mSpeechRecognizer != null)
{
mSpeechRecognizer.destroy();
}
Log.d("onDestroy","Entered");
}
protected class SpeechRecognitionListener implements RecognitionListener
{
private static final String TAG = "Sppech---->";
#Override
public void onBeginningOfSpeech()
{
// speech input will be processed, so there is no need for count down anymore
if (mIsCountDownOn)
{
mIsCountDownOn = false;
mNoSpeechCountDown.cancel();
}
//Log.d(TAG, "onBeginingOfSpeech"); //$NON-NLS-1$
Log.d("onBeginningOfSpeech","Entered");
}
#Override
public void onBufferReceived(byte[] buffer)
{
String sTest = "";
Log.d("onBufferReceived","Entered");
}
#Override
public void onEndOfSpeech()
{
//Log.d(TAG, "onEndOfSpeech"); //$NON-NLS-1$
Log.d("onEndOfSpeech","Entered");
}
#Override
public void onError(int error)
{
if (mIsCountDownOn)
{
mIsCountDownOn = false;
mNoSpeechCountDown.cancel();
}
mIsListening = false;
Message message = Message.obtain(null, MSG_RECOGNIZER_START_LISTENING);
try
{
mServerMessenger.send(message);
}
catch (RemoteException e)
{
}
//Log.d(TAG, "error = " + error); //$NON-NLS-1$
Log.d("onError","Entered");
}
#Override
public void onEvent(int eventType, Bundle params)
{
}
#Override
public void onPartialResults(Bundle partialResults)
{
}
#Override
public void onReadyForSpeech(Bundle params)
{
if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.JELLY_BEAN)
{
mIsCountDownOn = true;
mNoSpeechCountDown.start();
mAudioManager.setStreamMute(AudioManager.STREAM_SYSTEM, false);
}
//Log.d("TAG", "onReadyForSpeech");
Toast.makeText(getApplicationContext(), "Ready for Speech", Toast.LENGTH_SHORT).show();
Log.d("onReadyForSpeech","Entered");//$NON-NLS-1$
}
#Override
public void onResults(Bundle results)
{
//Log.d(TAG, "onResults"); //$NON-NLS-1$
}
#Override
public void onRmsChanged(float rmsdB)
{
}
}
#Override
public IBinder onBind(Intent intent) {
// TODO Auto-generated method stub
return null;
}
}

You get it in onResult(Bundle result), which you can then get what the user speak into an ArrayList
ArrayList<String> matches = result.getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION);

Running Android Speech Recognition as Service: will not start

I'm using the solution here: Android Speech Recognition as a service on Android 4.1 & 4.2 The code below gets to the onStartCommand() method, however the speech recogntion never seems to kick off, as evidenced by the fact that the onReadyForSpeech() method is never called.
UPDATE:
So I added and that allowed the onReadyForSpeech() to be called , BUT onError() is called with error code: 6 after the onReadyForSpeech() method is complete (this goes into a continuous loop because the start listening code is started again after onError() is called). Like Hoan Nguyen states below, error code 6 is ERROR_SPEECH_TIMEOUT BUT I never see a speech recognition dialog come up so I know to start speaking. I also tried to start speaking immediately after kicking off this code without that dialog coming and still get error code 6, what am I doing wrong here?
UPDATE (9-06-13):
Like Hoan stated, there is no dialog that comes up. You just start talking as soon as listening is called. But I ran into another issue where trying to restart the listener after every onResult() is called...That issue and the complete code for this can be found here: Android Speech Speech Recognition: Repeated Calling of SpeechRecognizer.startListening() fails on JB 4.1.2
My activity code that calls the service:
startService(new Intent(VoiceRecognition.this, VoiceRecogService.class));
My service:
public class VoiceRecogService extends Service
{
protected AudioManager mAudioManager;
protected SpeechRecognizer mSpeechRecognizer;
protected Intent mSpeechRecognizerIntent;
protected final Messenger mServerMessenger = new Messenger(new IncomingHandler(this));
protected boolean mIsListening;
protected volatile boolean mIsCountDownOn;
static final int MSG_RECOGNIZER_START_LISTENING = 1;
static final int MSG_RECOGNIZER_CANCEL = 2;
private int mBindFlag;
private Messenger mServiceMessenger;
#Override
public void onCreate()
{
super.onCreate();
mAudioManager = (AudioManager) getSystemService(Context.AUDIO_SERVICE);
mSpeechRecognizer = SpeechRecognizer.createSpeechRecognizer(this);
mSpeechRecognizer.setRecognitionListener(new SpeechRecognitionListener());
mSpeechRecognizerIntent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
mSpeechRecognizerIntent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL,
RecognizerIntent.LANGUAGE_MODEL_FREE_FORM);
mSpeechRecognizerIntent.putExtra(RecognizerIntent.EXTRA_CALLING_PACKAGE,
this.getPackageName());
//mSpeechRecognizer.startListening(mSpeechRecognizerIntent);
}
protected static class IncomingHandler extends Handler
{
private WeakReference<VoiceRecogService> mtarget;
IncomingHandler(VoiceRecogService target)
{
mtarget = new WeakReference<VoiceRecogService>(target);
}
#Override
public void handleMessage(Message msg)
{
final VoiceRecogService target = mtarget.get();
switch (msg.what)
{
case MSG_RECOGNIZER_START_LISTENING:
if (Build.VERSION.SDK_INT >= 16);//Build.VERSION_CODES.JELLY_BEAN)
{
// turn off beep sound
target.mAudioManager.setStreamMute(AudioManager.STREAM_SYSTEM, true);
}
if (!target.mIsListening)
{
target.mSpeechRecognizer.startListening(target.mSpeechRecognizerIntent);
target.mIsListening = true;
//Log.d(TAG, "message start listening"); //$NON-NLS-1$
}
break;
case MSG_RECOGNIZER_CANCEL:
target.mSpeechRecognizer.cancel();
target.mIsListening = false;
//Log.d(TAG, "message canceled recognizer"); //$NON-NLS-1$
break;
}
}
}
// Count down timer for Jelly Bean work around
protected CountDownTimer mNoSpeechCountDown = new CountDownTimer(5000, 5000)
{
#Override
public void onTick(long millisUntilFinished)
{
// TODO Auto-generated method stub
}
#Override
public void onFinish()
{
mIsCountDownOn = false;
Message message = Message.obtain(null, MSG_RECOGNIZER_CANCEL);
try
{
mServerMessenger.send(message);
message = Message.obtain(null, MSG_RECOGNIZER_START_LISTENING);
mServerMessenger.send(message);
}
catch (RemoteException e)
{
}
}
};
#Override
public int onStartCommand (Intent intent, int flags, int startId)
{
//mSpeechRecognizer.startListening(mSpeechRecognizerIntent);
try
{
Message msg = new Message();
msg.what = MSG_RECOGNIZER_START_LISTENING;
mServerMessenger.send(msg);
}
catch (RemoteException e)
{
}
return START_NOT_STICKY;
}
#Override
public void onDestroy()
{
super.onDestroy();
if (mIsCountDownOn)
{
mNoSpeechCountDown.cancel();
}
if (mSpeechRecognizer != null)
{
mSpeechRecognizer.destroy();
}
}
protected class SpeechRecognitionListener implements RecognitionListener
{
#Override
public void onBeginningOfSpeech()
{
// speech input will be processed, so there is no need for count down anymore
if (mIsCountDownOn)
{
mIsCountDownOn = false;
mNoSpeechCountDown.cancel();
}
//Log.d(TAG, "onBeginingOfSpeech"); //$NON-NLS-1$
}
#Override
public void onBufferReceived(byte[] buffer)
{
String sTest = "";
}
#Override
public void onEndOfSpeech()
{
Log.d("TESTING: SPEECH SERVICE", "onEndOfSpeech"); //$NON-NLS-1$
}
#Override
public void onError(int error)
{
if (mIsCountDownOn)
{
mIsCountDownOn = false;
mNoSpeechCountDown.cancel();
}
mIsListening = false;
Message message = Message.obtain(null, MSG_RECOGNIZER_START_LISTENING);
try
{
mServerMessenger.send(message);
}
catch (RemoteException e)
{
}
//Log.d(TAG, "error = " + error); //$NON-NLS-1$
}
#Override
public void onEvent(int eventType, Bundle params)
{
}
#Override
public void onPartialResults(Bundle partialResults)
{
}
#Override
public void onReadyForSpeech(Bundle params)
{
if (Build.VERSION.SDK_INT >= 16);//Build.VERSION_CODES.JELLY_BEAN)
{
mIsCountDownOn = true;
mNoSpeechCountDown.start();
mAudioManager.setStreamMute(AudioManager.STREAM_SYSTEM, false);
}
Log.d("TESTING: SPEECH SERVICE", "onReadyForSpeech"); //$NON-NLS-1$
}
#Override
public void onResults(Bundle results)
{
//Log.d(TAG, "onResults"); //$NON-NLS-1$
}
#Override
public void onRmsChanged(float rmsdB)
{
}
}
#Override
public IBinder onBind(Intent arg0) {
// TODO Auto-generated method stub
return null;
}
}

Develop Reference

The Android operating system is a mobile operating system that was developed by Google (GOOGL?) to be primarily used for touchscreen devices, cell phones, and tablets.

Handling Errors in PocketSphinx Android app - android

Crash is a bug in pocketsphinx-android. If you update to latest version from github, it should properly throw RuntimeException on any errors in methods addKeyphrase and setSearch.

Related

PocketSphinx on Android recognises words even if they aren't spoken

Loop SpeechRecognizer in Android [duplicate]

Speech recognizer: not connected to the recognition service error after onPause

Getting speech to text Android

Running Android Speech Recognition as Service: will not start

Categories

Resources