Android Speech Recognition as a service on Android 4.1 & 4.2

Graham Laming picture Graham Laming · Feb 18, 2013 · Viewed 64.4k times · Source

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.

Answer

Hoan Nguyen picture Hoan Nguyen · Feb 19, 2013

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