android - It's possible to make SpeechRecognizer faster?

Question

I'm developing an application which is using the android SpeechRecognizer. I'm using it for something simple. I click in a button, my SpeechRecognizer start listening and I got some results from what I said.

Easy right? Well, My problem is that I need to make SpeechRecognizer fast. I mean, I click in my button, I say "Hello" and SpeechRecognizer takes like 3-4 seconds in return an array with the possible results. My question is:

It's possible to make SpeechRecognizer return results more faster? Or take less time to close the Listening intent and start to process what it listen? Maybe another way to do it? which will have a better performance than this?

I was checking the library and I saw this 3 parameters:

EXTRA_SPEECH_INPUT_MINIMUM_LENGTH_MILLIS:

The amount of time that it should take after we stop hearing speech to consider the input complete.

EXTRA_SPEECH_INPUT_COMPLETE_SILENCE_LENGTH_MILLIS

The minimum length of an utterance.

EXTRA_SPEECH_INPUT_POSSIBLY_COMPLETE_SILENCE_LENGTH_MILLIS

The amount of time that it should take after we stop hearing speech to consider the input possibly complete.

http://developer.android.com/intl/es/reference/android/speech/RecognizerIntent.html

I have tried all of them but it is not working, or maybe I'm not using them right. Here is my code:

public class MainActivity extends Activity {
private static final String TIME_FORMAT = "%02d:%02d:%02d";
private final String TAG = "MainActivity";

private StartTimerButton mSpeakButton;
private CircleProgressBar mCountdownProgressBar;
private CountDownTimer mCountDownTimer;
private TextView mTimer;
private int mRunSeconds = 0;
private SpeechRecognizer mSpeechRecognizer;
private Intent mSpeechRecognizerIntent;
private boolean mIsListening = false;

@Override
protected void onCreate(Bundle savedInstanceState) {
    super.onCreate(savedInstanceState);
    setContentView(R.layout.activity_main);
    mRunSeconds = 0;
    mTimer = (TextView) findViewById(R.id.timerText);
    mCountdownProgressBar = (CircleProgressBar) findViewById(R.id.progressBar);
    mSpeechRecognizer = SpeechRecognizer.createSpeechRecognizer(this);
    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());

//          mSpeechRecognizerIntent.putExtra(RecognizerIntent.EXTRA_SPEECH_INPUT_MINIMUM_LENGTH_MILLIS,
//                1000);
//        mSpeechRecognizerIntent.putExtra(RecognizerIntent.EXTRA_SPEECH_INPUT_COMPLETE_SILENCE_LENGTH_MILLIS,
//                1000);
//        mSpeechRecognizerIntent.putExtra(RecognizerIntent.EXTRA_SPEECH_INPUT_POSSIBLY_COMPLETE_SILENCE_LENGTH_MILLIS,
//                1000);

    SpeechRecognitionListener listener = new SpeechRecognitionListener();
    mSpeechRecognizer.setRecognitionListener(listener);
    mSpeakButton = (StartTimerButton) findViewById(R.id.btnSpeak);
    mSpeakButton.setReadyState(false);
    mSpeakButton.setOnClickListener(new View.OnClickListener() {

        @Override
        public void onClick(View v) {
            if (mSpeakButton.isReady()) {
                if (!mIsListening)
                    mSpeechRecognizer.startListening(mSpeechRecognizerIntent);
            } else
                mSpeakButton.setReadyState(true);
        }
    });

}     

@Override
public boolean onCreateOptionsMenu(Menu menu) {
    // Inflate the menu; this adds items to the action bar if it is present.
    return true;
}

public void onSpeechResults(ArrayList<String> matches) {
    for (String match : matches) {

        match = match.toLowerCase();
        Log.d(TAG, "Got speech: " + match);

        if (match.contains("go")) {
            //Do Something
            mSpeechRecognizer.stopListening();
        }
        if (match.contains("stop")) {
            //Do Something
            mSpeechRecognizer.stopListening();
        }
    }
}

protected class SpeechRecognitionListener implements RecognitionListener
{

    @Override
    public void onBeginningOfSpeech()
    {
        //Log.d(TAG, "onBeginingOfSpeech");
    }

    @Override
    public void onBufferReceived(byte[] buffer)
    {

    }

    @Override
    public void onEndOfSpeech()
    {
        //Log.d(TAG, "onEndOfSpeech");
    }

    @Override
    public void onError(int error)
    {
        mSpeechRecognizer.startListening(mSpeechRecognizerIntent);

        //Log.d(TAG, "error = " + error);
    }

    @Override
    public void onEvent(int eventType, Bundle params)
    {

    }

    @Override
    public void onPartialResults(Bundle partialResults)
    {
        ArrayList<String> matches = partialResults.getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION);
        for (String match : matches) {
            match = match.toLowerCase();
            Log.d(TAG, "onPartialResults : " + match);
        }
    }

    @Override
    public void onReadyForSpeech(Bundle params)
    {
        Log.d(TAG, "onReadyForSpeech"); //$NON-NLS-1$
    }

    @Override
    public void onResults(Bundle results)
    {
        //Log.d(TAG, "onResults"); //$NON-NLS-1$
        ArrayList<String> matches = results.getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION);
        onSpeechResults(matches);
        // matches are the return values of speech recognition engine
        // Use these values for whatever you wish to do
    }

    @Override
    public void onRmsChanged(float rmsdB)
    {
    }
}}

Answer 1

Yes, it is possible to reduce the delay before shutdown....

You cannot alter the amount of time that Google considers to be silence at the end of a user speaking. The EXTRA_SPEECH_* parameters used to work, now they appear to sporadically work at best, or not work at all.

What you can do, is use the partial results to detect the words or phrase you want and then manually shut down the recognition service.

Here's an example of how to do this:

public boolean isHelloDetected(@NonNull final Context ctx, @NonNull final Locale loc, @NonNull final Bundle results) {

        boolean helloDetected = false;

        if (!results.isEmpty()) {

            final String hello = ctx.getString(R.string.hello);

            final ArrayList<String> partialData = results.getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION);

                /* handles empty string bug */
            if (partialData != null && !partialData.isEmpty()) {
                partialData.removeAll(Collections.singleton(""));

                if (!partialData.isEmpty()) {
                    final ListIterator<String> itr = partialData.listIterator();

                    String vd;
                    while (itr.hasNext()) {
                        vd = itr.next().toLowerCase(loc).trim();

                        if (vd.startsWith(hello)) {
                            helloDetected = true;
                            break;
                        }
                    }
                }
            }

            if (!helloDetected) {
                final ArrayList<String> unstableData = results.getStringArrayList("android.speech.extra.UNSTABLE_TEXT");

                    /* handles empty string bug */
                if (unstableData != null && !unstableData.isEmpty()) {
                    unstableData.removeAll(Collections.singleton(""));

                    if (!unstableData.isEmpty()) {
                        final ListIterator<String> itr = unstableData.listIterator();

                        String vd;
                        while (itr.hasNext()) {
                            vd = itr.next().toLowerCase(loc).trim();

                            if (vd.startsWith(hello)) {
                                helloDetected = true;
                                break;
                            }
                        }
                    }
                }
            }
        }

        return helloDetected;
    }

You would run this method each time you receive from onPartialResults()

If true is returned, you'll need to call stopListening() on the main thread (probably by new Handler(Looper.getMainLooper()).post(...

Be aware though, once you've shut down the recognizer, the subsequent and final results you receive in onResults() may not contain "hello". As that word may have only be classified as unstable.

You'll need to write additional logic to prevent using detectHello() once hello has been detected (otherwise you'll repeatedly call stopListening()) - some simple boolean markers would resolve this.

Finally, the use of Collections.singleton("") to remove empty strings is part of an internal bug report, details to replicate here and the use of a ListIterator may be overkill for just your sample; a simple for loop would suffice.

Good luck.