0

I am currently developing a word translator with speech-to-text function. I studied pocketsphinx but I can only let it search the dictionary by declaring a default keyword. Is there a way that you will speak first before it will search the dictionary? I am stucked here. Any help will be appreciated. Thankyou! Here's the code:

/* Named searches allow to quickly reconfigure the decoder */
private static final String KWS_SEARCH = "wakeup";
private static final String FORECAST_SEARCH = "forecast";
private static final String DIGITS_SEARCH = "digits";
private static final String PHONE_SEARCH = "phones";
private static final String MENU_SEARCH = "menu";

/* Keyword we are looking for to activate menu */
private static final String KEYPHRASE = "";

/* Used to handle permission request */
private static final int PERMISSIONS_REQUEST_RECORD_AUDIO = 1;

private SpeechRecognizer recognizer;
private HashMap<String, Integer> captions;

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(TranslateActivity.this);
                File assetDir = assets.syncAssets();
                setupRecognizer(assetDir);
            } catch (IOException e) {
                return e;
            }
            return null;
        }

        @Override
        protected void onPostExecute(Exception result) {
            if (result != null) {
                Toast.makeText(TranslateActivity.this,"Failed to initialize recognizer " + result, Toast.LENGTH_SHORT).show();
                popupWindow.dismiss();

            } else {
                lblPrepare.setText("VOICE RECOGNITION READY");
                lblSpeak.setVisibility(View.VISIBLE);
                recognizer.startListening(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();
    if(text.equals(""))
    {

    }else
    {
        Toast.makeText(TranslateActivity.this, text, Toast.LENGTH_SHORT).show();
    }
    /*if (text.equals(KEYPHRASE)){
        recognizer.cancel();
            // <- You have to implement this
        recognizer.startListening(KWS_SEARCH);
    }/*
        switchSearch(MENU_SEARCH);
    else if (text.equals(DIGITS_SEARCH))
        switchSearch(DIGITS_SEARCH);
    else if (text.equals(PHONE_SEARCH))
        switchSearch(PHONE_SEARCH);
    else if (text.equals(FORECAST_SEARCH))
        switchSearch(FORECAST_SEARCH);
    else
        Toast.makeText(TranslateActivity.this,text, Toast.LENGTH_SHORT).show();*/
}

/**
 * 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();
    }*/

    if (hypothesis!=null)
    {
        popupWindow.dismiss();
        performAction(hypothesis);
    }
}

@Override
public void onBeginningOfSpeech() {
}

/**
 * We stop recognizer here to get a final result
 */
@Override
public void onEndOfSpeech() {
    /*if (!recognizer.getSearchName().equals(KWS_SEARCH))
        switchSearch(KWS_SEARCH);*/
    recognizer.stop();
    popupWindow.dismiss();
}
/*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);


    Toast.makeText(TranslateActivity.this,searchName, Toast.LENGTH_SHORT).show();
}*/

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)
            .setKeywordThreshold(1e-45f) // Threshold to tune for keyphrase to balance between false alarms and misses
            .setBoolean("-allphone_ci", true)  // Use context-independent phonetic search, context-dependent is too slow for mobile


            .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, KEYPHRASE);

    // Create grammar-based search for selection between demos
   /* File menuGrammar = new File(assetsDir, "menu.gram");
    recognizer.addGrammarSearch(MENU_SEARCH, menuGrammar);

    // Create grammar-based search for digit recognition
    File digitsGrammar = new File(assetsDir, "digits.gram");
    recognizer.addGrammarSearch(DIGITS_SEARCH, digitsGrammar);

    // Create language model search
    File languageModel = new File(assetsDir, "weather.dmp");
    recognizer.addNgramSearch(FORECAST_SEARCH, languageModel);

    // Phonetic search
    File phoneticModel = new File(assetsDir, "en-phone.dmp");
    recognizer.addAllphoneSearch(PHONE_SEARCH, phoneticModel);*/
}

@Override
public void onError(Exception error) {
    Toast.makeText(TranslateActivity.this,"Failed: "+error.getMessage(), Toast.LENGTH_SHORT).show();
}

@Override
public void onTimeout() {
   /* switchSearch(KWS_SEARCH);*/
}

public void performAction(Hypothesis hypothesis) {
    String strWord = hypothesis.getHypstr();
    txtOriginal.setText(strWord);

    if(recognizer.getDecoder().lookupWord("abc") == null) {
        // do something
    }
    Toast.makeText(TranslateActivity.this, strWord, Toast.LENGTH_SHORT).show();
}
  • Possible duplicate of [CMUSphinx PocketSphinx - Recognize all (or large amount) of words](http://stackoverflow.com/questions/25949295/cmusphinx-pocketsphinx-recognize-all-or-large-amount-of-words) – Nikolay Shmyrev Aug 29 '16 at 19:45
  • Possible duplicate of [Android speech recognizing and audio recording in the same time](http://stackoverflow.com/questions/7160741/android-speech-recognizing-and-audio-recording-in-the-same-time) – Name is Nilay Sep 23 '16 at 11:40

0 Answers0