Yesterday i ask a simplified question of my problem, but think its too simplified.
What my programm should do, is to hear a keyword and when he hear it, he should listen to what i said. (like if you told to siri or google now, by saying siri or ok google).
I'm using pocketsphinx for the keyword and the google speechrecognizer for the longer parts. It works, but only for one time. The pocketsphinx is in the MainActivity and the google recognizer is in an extra class (Jarvis).
The programm starts with the pocketsphinx listener, when he hear the KEYPHRASE, he starts the google listener by calling jarvis.startListener() (by the next()-method) and there is the problem, when the googlelistener is done, i dont come back from the Jarvis-class to the MainActivity to call the next() method again.
(when the google recognizer is done, the last things he do is in the onResult() in Jarvis-class, but from there i cant call the next()-method from MainActivity-class)
MainActivity
package com.example.superuser.jarvis;
import android.app.Activity;
import android.os.AsyncTask;
import android.os.Bundle;
import android.speech.RecognitionListener;
import android.view.View;
import android.widget.Button;
import android.widget.TextView;
import android.widget.Toast;
import java.io.File;
import java.io.IOException;
import edu.cmu.pocketsphinx.Assets;
import edu.cmu.pocketsphinx.Hypothesis;
import edu.cmu.pocketsphinx.SpeechRecognizer;
import edu.cmu.pocketsphinx.SpeechRecognizerSetup;
import static android.widget.Toast.makeText;
import static edu.cmu.pocketsphinx.SpeechRecognizerSetup.defaultSetup;
public class MainActivity extends Activity implements edu.cmu.pocketsphinx.RecognitionListener {
private String LOG_TAG = "Jarvis_hears_anything";
private TextView tv;
private Jarvis jarvis;
private boolean wannahearjarvis = false;
/* Named searches allow to quickly reconfigure the decoder */
private static final String KWS_SEARCH = "wakeup";
/* Keyword we are looking for to activate menu */
private static final String KEYPHRASE = "jarvis";
private edu.cmu.pocketsphinx.SpeechRecognizer recognizer;
//private HashMap<String, Integer> captions;
@Override
protected void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
setContentView(R.layout.activity_main);
final Button button = (Button) findViewById(R.id.b1);
tv = (TextView) findViewById(R.id.tv1);
//captions = new HashMap<String, Integer>();
//captions.put(KWS_SEARCH, R.string.kws_caption);
jarvis = new Jarvis(getApplicationContext());
new AsyncTask<Void, Void, Exception>() {
@Override
protected Exception doInBackground(Void... params) {
try {
Assets assets = new Assets(MainActivity.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.tv1))
.setText("Failed to init recognizer " + result);
} else {
//switchSearch(KWS_SEARCH);
recognizer.startListening(KWS_SEARCH);
}
}
}.execute();
button.setOnClickListener(new View.OnClickListener() {
@Override
public void onClick(View v) {
Toast.makeText(getApplicationContext(), "geht", Toast.LENGTH_SHORT).show();
}
});
}
public void next(){
if (wannahearjarvis){
recognizer.startListening(KWS_SEARCH);
wannahearjarvis = false;
}
else{
jarvis.startListening();
wannahearjarvis = true;
}
}
@Override
public void onDestroy() {
super.onDestroy();
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(KEYPHRASE)){
tv.append("found");
recognizer.stop();
//switchSearch(KWS_SEARCH);
}
else {
//((TextView) findViewById(R.id.tv1)).append(text+"PR");
//Log.i(LOG_TAG, text+"PR");
}
}
/**
* This callback is called when we stop the recognizer.
*/
@Override
public void onResult(Hypothesis hypothesis) {
//((TextView) findViewById(R.id.tv1)).setText("");
((TextView) findViewById(R.id.tv1)).append("oR");
if (hypothesis != null) {
String text = hypothesis.getHypstr();
makeText(getApplicationContext(), text, Toast.LENGTH_SHORT).show();
}
next();
}
@Override
public void onBeginningOfSpeech() {
}
/**
* We stop recognizer here to get a final result
*/
@Override
public void onEndOfSpeech() {
if (!recognizer.getSearchName().equals(KWS_SEARCH)){
tv.append("fuck");
}
//switchSearch(KWS_SEARCH);
}
/*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);
//String caption = getResources().getString(captions.get(searchName));
//((TextView) findViewById(R.id.tv1)).setText(caption);
//((TextView) findViewById(R.id.tv1)).append(caption);
}*/
private void setupRecognizer(File assetsDir) throws IOException {
// The recognizer can be configured to perform multiple searches
// of different kind and switch between them
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-20f)
// Use context-independent phonetic search, context-dependent is too slow for mobile
.setBoolean("-allphone_ci", true)
.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);
}
@Override
public void onError(Exception error) {
((TextView) findViewById(R.id.tv1)).setText(error.getMessage());
}
@Override
public void onTimeout() {
//switchSearch(KWS_SEARCH);
}
}
Jarvis
package com.example.superuser.jarvis;
import android.content.Context;
import android.content.Intent;
import android.media.AudioManager;
import android.os.Bundle;
import android.speech.RecognitionListener;
import android.speech.RecognizerIntent;
import android.speech.SpeechRecognizer;
import android.widget.Toast;
import java.util.ArrayList;
public class Jarvis implements RecognitionListener{
private AudioManager audiom;
private SpeechRecognizer speech;
private Intent recogIntent;
private Toast m;
private Context c;
private String text;
public Jarvis(Context context){
speech = SpeechRecognizer.createSpeechRecognizer(context);
speech.setRecognitionListener(this);
recogIntent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
recogIntent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_PREFERENCE, "de");
//recogIntent.putExtra(RecognizerIntent.EXTRA_CALLING_PACKAGE, context.getPackageName());
m = new Toast(context);
c=context;
}
public void startListening(){
speech.startListening(recogIntent);
}
public void destroy(){
speech.stopListening();
speech.cancel();
speech.destroy();
}
@Override
public void onReadyForSpeech(Bundle params) {
}
@Override
public void onBeginningOfSpeech() {
}
@Override
public void onRmsChanged(float rmsdB) {
}
@Override
public void onBufferReceived(byte[] buffer) {
}
@Override
public void onEndOfSpeech() {
}
@Override
public void onError(int error) {
}
@Override
public void onResults(Bundle results) {
ArrayList<String> matches = results
.getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION);
Toast.makeText(c, matches.get(0), Toast.LENGTH_LONG).show();
speech.cancel();
//tried
//MainActivity m = new MainActivity();
//m.next();
//but got a Nullpointer Exception
}
@Override
public void onPartialResults(Bundle partialResults) {
}
@Override
public void onEvent(int eventType, Bundle params) {
}
}
