Restart SpeechRecognizer using onUtteranceProgressListener - android

I've been working on this code for weeks with no progress at all, even though it seems like such an easy fix!! Basically I am using TextToSpeech with SpeechRecognizer in order to have the app ask me a question and then listen for my answer. Here's my code... I'm thinking its a thread problem or something.
Basically when I hold down the button, SPeechRecognizer starts listening until i take away finger... this works fine.. but I programmatically want the SpeechRecognizer to start up again after Utterance is Completed or simulate a button press to get it to work but neither works...
public class MainActivity extends AppCompatActivity {
TextToSpeech textToSpeech;
// SpeechRecognizer
SpeechRecognizer mSpeechRecognizer;
Intent mSpeechRecognizerIntent;
// Speech Analysis Support
SpeechToTextAnalyzer speechToTextAnalyzer;
String speechToTextAnalyzerResponse;
String SPEECH_RESPONSE_BACK;
int buttonPressCounter;
boolean responsive;
TextView StatusDisplay, WordingDisplay;
Button SimulateButton;
#Override
protected void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
setContentView(R.layout.activity_main);
checkPermission();
buttonPressCounter = 0;
// Initialize TextToSpeech
textToSpeech = new TextToSpeech(getApplicationContext(), new TextToSpeech.OnInitListener() {
#Override
public void onInit(int status) {
if(status != TextToSpeech.ERROR) {
textToSpeech.setLanguage(Locale.CANADA);
}
textToSpeech.setOnUtteranceProgressListener(new UtteranceProgressListener() {
#Override
public void onStart(String utteranceId) {
// Speaking started.
}
#Override
public void onDone(String utteranceId) {
// Speaking stopped.
if(responsive){ // if(utteranceId == "LISTEN_FOR_NEW_RESPONSE")
// possible method one:
SimulateButton.performClick();
// possible method two:
//mSpeechRecognizer.startListening(mSpeechRecognizerIntent);
// NOTE: SO FAR NEITHER OF THESE LINES MAKE THE SPEECHRECOGNIZER START UP WITHOUT ME TOUCHING THE BUTTON!!!
}
}
#Override
public void onError(String utteranceId) {
// There was an error.
}
});
}
});
// Initialize UI View Components
StatusDisplay = (TextView)findViewById(R.id.StatusUpdater);
WordingDisplay = (TextView)findViewById(R.id.WordsHeard);
// Create Reference to Classes
speechToTextAnalyzer = new SpeechToTextAnalyzer(this, this);
// Initialize SpeechRecognizer and Intent
final SpeechRecognizer mSpeechRecognizer = SpeechRecognizer.createSpeechRecognizer(this);
final Intent mSpeechRecognizerIntent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
mSpeechRecognizerIntent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL,
RecognizerIntent.LANGUAGE_MODEL_FREE_FORM);
mSpeechRecognizerIntent.putExtra(RecognizerIntent.EXTRA_LANGUAGE,
Locale.getDefault());
mSpeechRecognizerIntent.putExtra(RecognizerIntent.EXTRA_MAX_RESULTS, 1);
mSpeechRecognizer.setRecognitionListener(new RecognitionListener() {
#Override
public void onReadyForSpeech(Bundle bundle) {
}
#Override
public void onBeginningOfSpeech() {
}
#Override
public void onRmsChanged(float v) {
}
#Override
public void onBufferReceived(byte[] bytes) {
}
#Override
public void onEndOfSpeech() {
}
#Override
public void onError(int errorCode) {
String errorMessage = getErrorText(errorCode);
//Log.d(LOG_TAG, "FAILED " + errorMessage);
//listeningOn = false; // UNSURE!!
}
// accompanying text for onError
public String getErrorText(int errorCode) {
String message;
switch (errorCode) {
case SpeechRecognizer.ERROR_AUDIO:
message = "Audio Recording Error";
break;
case SpeechRecognizer.ERROR_CLIENT:
message = "Client Side Error";
break;
case SpeechRecognizer.ERROR_INSUFFICIENT_PERMISSIONS:
message = "Insufficient Permissions";
break;
case SpeechRecognizer.ERROR_NETWORK:
message = "Network Error";
break;
case SpeechRecognizer.ERROR_NETWORK_TIMEOUT:
message = "Network TimeOut";
break;
case SpeechRecognizer.ERROR_NO_MATCH:
message = "No Match";
break;
case SpeechRecognizer.ERROR_RECOGNIZER_BUSY:
message = "RecognitionService Busy";
break;
case SpeechRecognizer.ERROR_SERVER:
message = "Error From Server";
break;
case SpeechRecognizer.ERROR_SPEECH_TIMEOUT:
message = "No Speech Input";
break;
default:
message = "Couldn't Understand, Please Try Again";
break;
}
return message;
}
#Override
public void onResults(Bundle bundle) {
//getting all the matches
ArrayList<String> matches = bundle
.getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION);
String firstMatch = "";
//displaying the first match
if (matches != null) {
for(int i = 0; i < matches.size(); i++){
firstMatch = matches.get(i); // get the last one, which has the actual words I spoke...
}
matches.clear();
}
//StatusDisplay.setText("Not Listening...");
// ENTRY POINT FOR ALL COMMAND FUNCTIONALITY
speechToTextAnalyzerResponse = speechToTextAnalyzer.AnalyzeSpeechSingleResponse(firstMatch);
buttonPressCounter = speechToTextAnalyzer.AnalyzeSpeechCounter(buttonPressCounter);
responsive = speechToTextAnalyzer.AnalyzeSpeechResponseThenListen(buttonPressCounter);
SPEECH_RESPONSE_BACK = speechToTextAnalyzerResponse;
WordingDisplay.setText(SPEECH_RESPONSE_BACK);
if(responsive){
RESPONSIVE_SPEECH("... okay now say something new ... ");
}
else {
SINGLE_RESPONSE();
}
}
#Override
public void onPartialResults(Bundle bundle) {
}
#Override
public void onEvent(int i, Bundle bundle) {
}
}); // end of mSpeechRecognizer.setRecognitionListener
SimulateButton = (Button)findViewById(R.id.DoSomething);
SimulateButton.setOnTouchListener(new View.OnTouchListener() {
#Override
public boolean onTouch(View view, MotionEvent motionEvent) {
switch (motionEvent.getAction()) {
case MotionEvent.ACTION_UP:
//when the user removed the finger
mSpeechRecognizer.stopListening();
StatusDisplay.setText("Not Listening...");
break;
case MotionEvent.ACTION_DOWN:
//finger is on the button
StatusDisplay.setText("Listening...");
mSpeechRecognizer.startListening(mSpeechRecognizerIntent);
// WHILE I HOLD BUTTON THIS ACTUALLY WORKS BUT NOT INSIDE ONUTTERANCEPROGRESSLISTENER.........
break;
}
return true;
}
});
} // end of onCreate()
public void SINGLE_RESPONSE(){
if (!textToSpeech.isSpeaking()) {
textToSpeech.speak(SPEECH_RESPONSE_BACK, TextToSpeech.QUEUE_FLUSH, null);
//textToSpeech.speak(WordingDisplay.getText().toString(), TextToSpeech.QUEUE_FLUSH, null);
} else {
textToSpeech.stop();
}
}
public void RESPONSIVE_SPEECH(String PleaseSayThis){
SPEECH_RESPONSE_BACK = PleaseSayThis;
// https://android-developers.googleblog.com/2009/09/introduction-to-text-to-speech-in.html
if (!textToSpeech.isSpeaking()) {
HashMap<String, String> stringStringHashMap = new HashMap<String, String>();
stringStringHashMap.put(TextToSpeech.Engine.KEY_PARAM_UTTERANCE_ID, "LISTEN_FOR_NEW_RESPONSE"); // when using normal text to speech, the ID is "ID_MAIN_CALL" to be searched for in onUtteranceCompleted
textToSpeech.speak(SPEECH_RESPONSE_BACK, textToSpeech.QUEUE_FLUSH, stringStringHashMap);
} else {
textToSpeech.stop();
}
}
private void checkPermission() {
if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.M) {
if (!(ContextCompat.checkSelfPermission(this, Manifest.permission.RECORD_AUDIO) == PackageManager.PERMISSION_GRANTED)) {
Intent intent = new Intent(Settings.ACTION_APPLICATION_DETAILS_SETTINGS,
Uri.parse("package:" + getPackageName()));
startActivity(intent);
finish();
}
}
}
protected void onDestroy(){
if(textToSpeech != null) {
textToSpeech.stop();
textToSpeech.shutdown();
textToSpeech = null;
}
super.onDestroy();
}

According to the UtteranceProgressListener docs, "The callbacks specified in this method can be called from multiple threads."
To verify this, you can add
boolean wasCalledFromBackgroundThread = (Thread.currentThread().getId() != 1);
Log.i("XXX", "was onDone() called on a background thread? : " + wasCalledFromBackgroundThread);
to the onDone() method body.
In my experience, they are called on background threads more often than not.
So, inside your onDone() method body, I would suggest surrounding the UI manipulation with runOnUiThread() like so:
#Override
public void onDone(String utteranceId) {
runOnUiThread(new Runnable() {
#Override
public void run() {
// possible method one:
SimulateButton.performClick();
// possible method two:
//mSpeechRecognizer.startListening(mSpeechRecognizerIntent);
}
});
}

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.

Speech recognition while transmitting voice from microphone through WebView WebRTC

I am writing an application, which has a WebView, that is handling a voice call via WebRTC. Microphone is working OK as I have granted permission to WebView.
webView.setWebChromeClient(new WebChromeClient() {
#Override
public void onPermissionRequest(final PermissionRequest request) {
request.grant(request.getResources());
}
Later I decided to add SpeechRecognizer so I can recognize what I am saying during the WebRTC call. I tried to make speech recognition work in the same activity, later I did it in a separate service, but unfortunally, it doesn't allow to work in a simultaneous way. Microphone gets occupied by WebView, and SpeechRecognizer doesn't get any sound (RMS is constantly -2.12). Or, if I try to run service before making call through WebView, the person I am calling to doesn't hear me at all (SpeechRecognizer occupies microphone and WebView doesn't get anything).
I hope to find any solution if it exists. I am not an iOS developer, but I've heard, that it's possible on iPhone, so it's a surprise, that is impossible on Android device.
My Speech Recognition service code
public class RecognitionService extends Service implements RecognitionListener {
private String LOG_TAG = "RecognitionService";
private SpeechRecognizer speech = null;
private Intent recognizerIntent;
public RecognitionService() {
}
#Override
public IBinder onBind(Intent intent) {
// TODO: Return the communication channel to the service.
startRecognition();
return null;
}
#Override
public void onCreate() {
Log.i("Test", "RecognitionService: onCreate");
startRecognition();
}
private void startRecognition() {
speech = SpeechRecognizer.createSpeechRecognizer(this);
speech.setRecognitionListener(this);
recognizerIntent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
recognizerIntent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_PREFERENCE,
"ru-RU");
recognizerIntent.putExtra(RecognizerIntent.EXTRA_CALLING_PACKAGE,
getPackageName());
recognizerIntent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL,
RecognizerIntent.LANGUAGE_MODEL_WEB_SEARCH);
recognizerIntent.putExtra(RecognizerIntent.EXTRA_MAX_RESULTS, 3);
speech.startListening(recognizerIntent);
}
#Override
public void onBeginningOfSpeech() {
Log.i(LOG_TAG, "onBeginningOfSpeech");
}
#Override
public void onBufferReceived(byte[] buffer) {
Log.i(LOG_TAG, "onBufferReceived: " + buffer);
}
#Override
public void onEndOfSpeech() {
Log.i(LOG_TAG, "onEndOfSpeech");
}
#Override
public void onError(int errorCode) {
String errorMessage = getErrorText(errorCode);
Log.d(LOG_TAG, "FAILED " + errorMessage);
speech.destroy();
startRecognition();
}
#Override
public void onEvent(int arg0, Bundle arg1) {
Log.i(LOG_TAG, "onEvent");
}
#Override
public void onPartialResults(Bundle arg0) {
Log.i(LOG_TAG, "onPartialResults");
}
#Override
public void onReadyForSpeech(Bundle arg0) {
Log.i(LOG_TAG, "onReadyForSpeech");
}
#Override
public void onResults(Bundle results) {
Log.i(LOG_TAG, "onResults");
ArrayList<String> matches = results
.getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION);
String text = "";
for (String result : matches)
text += result + "\n";
Toast.makeText(getApplicationContext(),text,Toast.LENGTH_SHORT).show();
speech.destroy();
startRecognition();
}
public static String getErrorText(int errorCode) {
String message;
switch (errorCode) {
case SpeechRecognizer.ERROR_AUDIO:
message = "Audio recording error";
break;
case SpeechRecognizer.ERROR_CLIENT:
message = "Client side error";
break;
case SpeechRecognizer.ERROR_INSUFFICIENT_PERMISSIONS:
message = "Insufficient permissions";
break;
case SpeechRecognizer.ERROR_NETWORK:
message = "Network error";
break;
case SpeechRecognizer.ERROR_NETWORK_TIMEOUT:
message = "Network timeout";
break;
case SpeechRecognizer.ERROR_NO_MATCH:
message = "No match";
break;
case SpeechRecognizer.ERROR_RECOGNIZER_BUSY:
message = "RecognitionService busy";
break;
case SpeechRecognizer.ERROR_SERVER:
message = "error from server";
break;
case SpeechRecognizer.ERROR_SPEECH_TIMEOUT:
message = "No speech input";
break;
default:
message = "Didn't understand, please try again.";
break;
}
return message;
}
#Override
public void onRmsChanged(float rmsdB) {
Log.i(LOG_TAG, "onRmsChanged: " + rmsdB);
}
}

Android speech to text :: getting text updated at realtime

I want to convert speech to text in my app..
For this i am using recognitionListener interface
Everything works fine but how to get the text updated and shown even while speaking( like in google now voice search)
I have set the RecognizerIntent.EXTRA_PARTIAL_RESULTS, to true
And also used the onPartialResults(Bundle arg() method of the recognitionListener interface to set text
By the whole text is getting displayed at once after speech recognition is complete
But i want the realtime text to be displayed as the user speaks
my activity
public class MainActivity extends Activity implements RecognitionListener
{
private TextView returnedText;
private ToggleButton toggleButton;
private ProgressBar progressBar;
private SpeechRecognizer speech = null;
private Intent recognizerIntent;
private String LOG_TAG = "VoiceRecognitionActivity";
#Override
protected void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
setContentView(R.layout.main);
returnedText = (TextView) findViewById(R.id.textView1);
progressBar = (ProgressBar) findViewById(R.id.progressBar1);
toggleButton = (ToggleButton) findViewById(R.id.toggleButton1);
Button recordbtn = (Button) findViewById(R.id.mainButton);
progressBar.setVisibility(View.INVISIBLE);
speech = SpeechRecognizer.createSpeechRecognizer(this);
speech.setRecognitionListener(this);
recognizerIntent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
recognizerIntent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_PREFERENCE,
"en");
recognizerIntent.putExtra(RecognizerIntent.EXTRA_CALLING_PACKAGE,
this.getPackageName());
recognizerIntent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL,
RecognizerIntent.LANGUAGE_MODEL_WEB_SEARCH);
recognizerIntent.putExtra(RecognizerIntent.EXTRA_PARTIAL_RESULTS, true);
recognizerIntent.putExtra(RecognizerIntent.EXTRA_SPEECH_INPUT_MINIMUM_LENGTH_MILLIS, 3000);
toggleButton.setOnCheckedChangeListener(new OnCheckedChangeListener() {
#Override
public void onCheckedChanged(CompoundButton buttonView,
boolean isChecked) {
if (isChecked) {
progressBar.setVisibility(View.VISIBLE);
progressBar.setIndeterminate(true);
speech.startListening(recognizerIntent);
} else {
progressBar.setIndeterminate(false);
progressBar.setVisibility(View.INVISIBLE);
speech.stopListening();
}
}
});
recordbtn.setOnLongClickListener(new OnLongClickListener(){
#Override
public boolean onLongClick(View p1)
{
progressBar.setVisibility(View.VISIBLE);
progressBar.setIndeterminate(true);
speech.startListening(recognizerIntent);
return true;
}
});
}
#Override
public void onResume() {
super.onResume();
}
#Override
protected void onPause() {
super.onPause();
if (speech != null) {
speech.destroy();
Log.i(LOG_TAG, "destroy");
}
}
#Override
public void onBeginningOfSpeech() {
Log.i(LOG_TAG, "onBeginningOfSpeech");
progressBar.setIndeterminate(false);
progressBar.setMax(10);
}
#Override
public void onBufferReceived(byte[] buffer) {
Log.i(LOG_TAG, "onBufferReceived: " + buffer);
}
#Override
public void onEndOfSpeech() {
Log.i(LOG_TAG, "onEndOfSpeech");
progressBar.setIndeterminate(true);
toggleButton.setChecked(false);
}
#Override
public void onError(int errorCode) {
String errorMessage = getErrorText(errorCode);
Log.d(LOG_TAG, "FAILED " + errorMessage);
returnedText.setText(errorMessage);
toggleButton.setChecked(false);
}
#Override
public void onEvent(int arg0, Bundle arg1) {
Log.i(LOG_TAG, "onEvent");
}
#Override
public void onPartialResults(Bundle arg0) {
Log.i(LOG_TAG, "onPartialResults");
ArrayList<String> matches = arg0.getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION);
String text = "";
for (String result : matches)
text += result + "\n";
returnedText.setText(text);
}
#Override
public void onReadyForSpeech(Bundle arg0) {
Log.i(LOG_TAG, "onReadyForSpeech");
}
#Override
public void onResults(Bundle results) {
Log.i(LOG_TAG, "onResults");
}
#Override
public void onRmsChanged(float rmsdB) {
Log.i(LOG_TAG, "onRmsChanged: " + rmsdB);
progressBar.setProgress((int) rmsdB);
}
public static String getErrorText(int errorCode) {
String message;
switch (errorCode) {
case SpeechRecognizer.ERROR_AUDIO:
message = "Audio recording error";
break;
case SpeechRecognizer.ERROR_CLIENT:
message = "Client side error";
break;
case SpeechRecognizer.ERROR_INSUFFICIENT_PERMISSIONS:
message = "Insufficient permissions";
break;
case SpeechRecognizer.ERROR_NETWORK:
message = "Network error";
break;
case SpeechRecognizer.ERROR_NETWORK_TIMEOUT:
message = "Network timeout";
break;
case SpeechRecognizer.ERROR_NO_MATCH:
message = "No match";
break;
case SpeechRecognizer.ERROR_RECOGNIZER_BUSY:
message = "RecognitionService busy";
break;
case SpeechRecognizer.ERROR_SERVER:
message = "error from server";
break;
case SpeechRecognizer.ERROR_SPEECH_TIMEOUT:
message = "No speech input";
break;
default:
message = "Didn't understand, please try again.";
break;
}
return message;
}
}
HOW TO MAKE THIS HAPPEN
You can't achieve a realtime recognition with google API. In the best case you can achieve the same result than google when you are using OK Google or for example Recognition in Whatsup for write Text word by word adding to your intent:
recognizerIntent.putExtra("android.speech.extra.DICTATION_MODE", true);
The Speechrecognizer take his time to process all the info and split it as info to be able to use it in your app. you can check the next post to see if it help you optimizing your app: Make SpeechRecognizer Faster
Hope that it will help you !

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.

how to integrate speech recognition with my app

I want to integrate speech recognition in my app.
for example: when user say specific word i put it in code like "hello"
it will capture a picture from my app.
I tried many code put about speech recognition but can't integrate it with my app
how to integrate into my app ?
how to make specific word to make capture ?
Show speech to text
public class MainActivity extends Activity {
private TextView txtSpeechInput;
private ImageButton btnSpeak;
private final int REQ_CODE_SPEECH_INPUT = 100;
#Override
protected void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
setContentView(R.layout.activity_main);
txtSpeechInput = (TextView) findViewById(R.id.txtSpeechInput);
btnSpeak = (ImageButton) findViewById(R.id.btnSpeak);
// hide the action bar
getActionBar().hide();
btnSpeak.setOnClickListener(new View.OnClickListener() {
#Override
public void onClick(View v) {
promptSpeechInput();
}
});
}
/**
* Showing google speech input dialog
* */
private void promptSpeechInput() {
Intent intent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
intent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL,
RecognizerIntent.LANGUAGE_MODEL_FREE_FORM);
intent.putExtra(RecognizerIntent.EXTRA_LANGUAGE, Locale.getDefault());
intent.putExtra(RecognizerIntent.EXTRA_PROMPT,
getString(R.string.speech_prompt));
try {
startActivityForResult(intent, REQ_CODE_SPEECH_INPUT);
} catch (ActivityNotFoundException a) {
Toast.makeText(getApplicationContext(),
getString(R.string.speech_not_supported),
Toast.LENGTH_SHORT).show();
}
}
/**
* Receiving speech input
* */
#Override
protected void onActivityResult(int requestCode, int resultCode, Intent data) {
super.onActivityResult(requestCode, resultCode, data);
switch (requestCode) {
case REQ_CODE_SPEECH_INPUT: {
if (resultCode == RESULT_OK && null != data) {
ArrayList<String> result = data
.getStringArrayListExtra(RecognizerIntent.EXTRA_RESULTS);
txtSpeechInput.setText(result.get(0));
}
break;
}
}
}
#Override
public boolean onCreateOptionsMenu(Menu menu) {
// Inflate the menu; this adds items to the action bar if it is present.
getMenuInflater().inflate(R.menu.main, menu);
return true;
}
}
Get speech in txtSpeechInput box .
I think this is going to help you
public class YourClassName RecognitionListener{
private SpeechRecognizer speech = null;
private Intent recognizerIntent;
private String LOG_TAG = "VoiceRecognitionActivity";
#Override
protected void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
requestWindowFeature(Window.FEATURE_NO_TITLE);
setContentView(R.layout.activity_camera);
speech = SpeechRecognizer.createSpeechRecognizer(this);
speech.setRecognitionListener(this);
recognizerIntent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
recognizerIntent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_PREFERENCE,
"en");
recognizerIntent.putExtra(RecognizerIntent.EXTRA_CALLING_PACKAGE, getApplication().getPackageName());
recognizerIntent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL,
RecognizerIntent.LANGUAGE_MODEL_WEB_SEARCH);
recognizerIntent.putExtra(RecognizerIntent.EXTRA_MAX_RESULTS, 3);
speech.startListening(recognizerIntent);
}
#Override
public void onReadyForSpeech(Bundle params) {
Log.i(LOG_TAG+">"+ "onReadyForSpeech");
}
#Override
public void onBeginningOfSpeech() {
Log.i(LOG_TAG+"> "+"onBeginningOfSpeech");
}
#Override
public void onRmsChanged(float rmsdB) {
Log.i(LOG_TAG+">"+ "onRmsChanged: " + rmsdB);
}
#Override
public void onBufferReceived(byte[] buffer) {
Log.i(LOG_TAG+">"+ "onBufferReceived: " + buffer);
}
#Override
public void onEndOfSpeech() {
Log.i(LOG_TAG+">"+ "onEndOfSpeech");
}
#Override
public void onError(int error) {
String errorMessage = getErrorText(error);
Log.d(LOG_TAG+">"+ "FAILED " + errorMessage);
if(errorMessage.contains("RecognitionService busy"))
{ speech.stopListening();
speech.startListening(recognizerIntent);
}else if(errorMessage.contains("No speech input")){
speech.stopListening();
speech.startListening(recognizerIntent);
}else if(errorMessage.contains("No match")){
speech.stopListening();
speech.startListening(recognizerIntent);
}
// speech.destroy();
// speech.startListening(recognizerIntent);
}
#Override
public void onResults(Bundle results) {
Log.i(LOG_TAG+">"+ "onResults");
ArrayList<String> matches = results
.getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION);
String text = "";
for (String result : matches)
text += result + "\n";
if(text.contains("your Keyword here")){
camera.takePicture(null, null, this);
Log.v(text+"these are results");
}
Log.v(text+"On result");
}
#Override
public void onPartialResults(Bundle partialResults) {
Log.i(LOG_TAG+">"+ "onPartialResults");
}
#Override
public void onEvent(int eventType, Bundle params) {
Log.i(LOG_TAG+">"+ "onEvent");
}
public String getErrorText(int errorCode) {
String message;
switch (errorCode) {
case SpeechRecognizer.ERROR_AUDIO:
message = "Audio recording error";
break;
case SpeechRecognizer.ERROR_CLIENT:
message = "Client side error";
break;
case SpeechRecognizer.ERROR_INSUFFICIENT_PERMISSIONS:
message = "Insufficient permissions";
break;
case SpeechRecognizer.ERROR_NETWORK:
message = "Network error";
break;
case SpeechRecognizer.ERROR_NETWORK_TIMEOUT:
message = "Network timeout";
break;
case SpeechRecognizer.ERROR_NO_MATCH:
message = "No match";
break;
case SpeechRecognizer.ERROR_RECOGNIZER_BUSY:
message = "RecognitionService busy";
break;
case SpeechRecognizer.ERROR_SERVER:
message = "error from server";
break;
case SpeechRecognizer.ERROR_SPEECH_TIMEOUT:
message = "No speech input";
break;
default:
message = "Didn't understand, please try again.";
break;
}
return message;
}
}

Categories

Resources