Develop Reference

Android( RecognitionListener) live speech to text preview

I'm using recognitionlistener interface in my app to convert speech to text. However I want to display the converted text from speech as soon as I speak. If I speak 4-5 words then 1st word should be displayed as soon as I speak it. In short like google assistant. I'm currently overriding it's onresults method and showing results when this method is called. Is there any way to detect one word at a time and show it one by one?
https://drive.google.com/open?id=0BxHdMJXrMP2HRk80aVBtZHIxaDAenter link description here
import android.app.Activity;
import android.content.Intent;
import android.os.Bundle;
import android.view.View;
import android.view.View.OnClickListener;
import android.speech.RecognitionListener;
import android.speech.RecognizerIntent;
import android.speech.SpeechRecognizer;
import android.widget.Button;
import android.widget.TextView;
import java.util.ArrayList;
import android.util.Log;
public class VoiceRecognitionTest extends Activity implements OnClickListener
{
private TextView mText;
private SpeechRecognizer sr;
private static final String TAG = "MyActivity";
#Override
public void onCreate(Bundle savedInstanceState)
{
super.onCreate(savedInstanceState);
setContentView(R.layout.main);
Button speakButton = (Button) findViewById(R.id.btn_speak);
mText = (TextView) findViewById(R.id.textView1);
speakButton.setOnClickListener(this);
sr = SpeechRecognizer.createSpeechRecognizer(this);
sr.setRecognitionListener(new listener());
}
class listener implements RecognitionListener
{
public void onReadyForSpeech(Bundle params)
{
Log.d(TAG, "onReadyForSpeech");
}
public void onBeginningOfSpeech()
{
Log.d(TAG, "onBeginningOfSpeech");
}
public void onRmsChanged(float rmsdB)
{
Log.d(TAG, "onRmsChanged");
}
public void onBufferReceived(byte[] buffer)
{
Log.d(TAG, "onBufferReceived");
}
public void onEndOfSpeech()
{
Log.d(TAG, "onEndofSpeech");
}
public void onError(int error)
{
Log.d(TAG, "error " + error);
mText.setText("error " + error);
}
public void onResults(Bundle results)
{
String str = new String();
Log.d(TAG, "onResults " + results);
ArrayList data = results.getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION);
for (int i = 0; i < data.size(); i++)
{
Log.d(TAG, "result " + data.get(i));
str += data.get(i);
}
mText.setText("results: "+String.valueOf(data.size()));
}
public void onPartialResults(Bundle partialResults)
{
Log.d(TAG, "onPartialResults");
}
public void onEvent(int eventType, Bundle params)
{
Log.d(TAG, "onEvent " + eventType);
}
}
public void onClick(View v) {
if (v.getId() == R.id.btn_speak)
{
Intent intent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
intent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL,RecognizerIntent.LANGUAGE_MODEL_FREE_FORM);
intent.putExtra(RecognizerIntent.EXTRA_CALLING_PACKAGE,"voice.recognition.test");
intent.putExtra(RecognizerIntent.EXTRA_MAX_RESULTS,5);
sr.startListening(intent);
}
}
}

Yes you can, you need to override onPartialResults :)
#Override
public void onPartialResults(Bundle partialResults) {
ArrayList data = partialResults.getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION);
String word = (String) data.get(data.size() - 1);
recognisedText.setText(word);
Log.i("TEST", "partial_results: " + word);
}

Voice Recognition: gap between words

I have a simple app for voice recognition that prints all the possible string ArrayList decoded. The problem is that it only works if I don't stop/pause between words. If I have a slight pause (very short as if I was speking normally) the app stops. I looked at the parameter SPEECH_INPUT_COMPLETE_SILENCE_LENGTH_MILLIS but it didn't change anything.
Any clue from a voice recognition specialist?
Here is my code:
package com.bernard.vtt;
import android.app.Activity;
import android.content.Intent;
import android.os.Bundle;
import android.speech.RecognitionListener;
import android.speech.RecognizerIntent;
import android.speech.SpeechRecognizer;
import android.view.View;
import android.widget.Button;
import android.widget.TextView;
import java.util.ArrayList;
public class MainActivity extends Activity implements RecognitionListener {
private TextView mText;
SpeechRecognizer speech = null;
private Intent recognizerIntent;
#Override
public void onCreate(Bundle savedInstanceState)
{
super.onCreate(savedInstanceState);
setContentView(R.layout.activity_main);
Button speakButton = (Button) findViewById(R.id.btn);
mText = (TextView) findViewById(R.id.textView1);
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_MAX_RESULTS, 3);
speakButton.setOnClickListener(new View.OnClickListener() {
#Override
public void onClick(View view) {
speech.startListening(recognizerIntent);
}
});
}
#Override
public void onResults(Bundle results) {
ArrayList<String> matches = results
.getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION);
String text = "";
assert matches != null;
for (String result : matches)
text += result + "\n";
mText.setText(text);
speech.stopListening();
}
#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 onPartialResults(Bundle partialResults) {
}
#Override
public void onEvent(int eventType, Bundle params) {
}

I believe the built-in speech recognition does not continually run. It is designed to hear one voice input and give results. If you want to continually listen, you need to restart recognition on each onResults callback. I also believe SPEECH_INPUT_COMPLETE_SILENCE_LENGTH_MILLIS has a max value, which is why changing it has little effect.

Android SpeechRecognizer always returns null

package com.example.voicerec;
import java.util.ArrayList;
import android.app.Activity;
import android.content.Intent;
import android.os.Bundle;
import android.speech.RecognitionListener;
import android.speech.RecognizerIntent;
import android.speech.SpeechRecognizer;
import android.util.Log;
public class MainActivity extends Activity {
private SpeechRecognizer mSpeechRecognizer;
#Override
protected void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
setContentView(R.layout.activity_main);
mSpeechRecognizer = SpeechRecognizer.createSpeechRecognizer(this);
mSpeechRecognizer.setRecognitionListener(new listener());
startrecording();
}
public void startrecording() {
Intent intent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
intent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL,
RecognizerIntent.LANGUAGE_MODEL_FREE_FORM);
intent.putExtra(RecognizerIntent.EXTRA_CALLING_PACKAGE,
getPackageName());
intent.putExtra(RecognizerIntent.EXTRA_MAX_RESULTS, 5);
mSpeechRecognizer.startListening(intent);
Log.i("log", "startgooglerec Started");
}
#Override
protected void onDestroy() {
super.onDestroy();
if (mSpeechRecognizer != null) {
mSpeechRecognizer.destroy();
}
}
class listener implements RecognitionListener {
#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);
System.out.println("results " + results);
System.out.println("matches " + matches);
}
#Override
public void onPartialResults(Bundle partialResults) {
}
#Override
public void onEvent(int eventType, Bundle params) {
}
}
}
Log:
03-25 09:53:51.489: I/System.out(12149): results Bundle[{results_recognition=null, confidence_scores=null}]
SpeechRecognizer always returns null in onresult, even if i talk also it returns null only, also i dose not stop listening. i can able to here listen to start sound but not stop sound. is there any thing wrong with my code, thanks in advance.

SpeechRecognizer gives fake results

I'm trying to find out how offline voice recognition works on Jelly Bean. After some googling, I started to use SpeechRecognizer but the onResults method of the RecognitionListener always gives me the same result : "abc".
I even tried this code (from here) :
package voice.recognition.test;
import android.app.Activity;
import android.content.Intent;
import android.os.Bundle;
import android.view.View;
import android.view.View.OnClickListener;
import android.speech.RecognitionListener;
import android.speech.RecognizerIntent;
import android.speech.SpeechRecognizer;
import android.widget.Button;
import android.widget.TextView;
import java.util.ArrayList;
import android.util.Log;
public class voiceRecognitionTest extends Activity implements OnClickListener
{
private TextView mText;
private SpeechRecognizer sr;
private static final String TAG = "MyStt3Activity";
#Override
public void onCreate(Bundle savedInstanceState)
{
super.onCreate(savedInstanceState);
setContentView(R.layout.main);
Button speakButton = (Button) findViewById(R.id.btn_speak);
mText = (TextView) findViewById(R.id.textView1);
speakButton.setOnClickListener(this);
sr = SpeechRecognizer.createSpeechRecognizer(this);
sr.setRecognitionListener(new listener());
}
class listener implements RecognitionListener
{
public void onReadyForSpeech(Bundle params)
{
Log.d(TAG, "onReadyForSpeech");
}
public void onBeginningOfSpeech()
{
Log.d(TAG, "onBeginningOfSpeech");
}
public void onRmsChanged(float rmsdB)
{
Log.d(TAG, "onRmsChanged");
}
public void onBufferReceived(byte[] buffer)
{
Log.d(TAG, "onBufferReceived");
}
public void onEndOfSpeech()
{
Log.d(TAG, "onEndofSpeech");
}
public void onError(int error)
{
Log.d(TAG, "error " + error);
mText.setText("error " + error);
}
public void onResults(Bundle results)
{
String str = new String();
Log.d(TAG, "onResults " + results);
ArrayList data = results.getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION);
for (int i = 0; i < data.size(); i++)
{
Log.d(TAG, "result " + data.get(i));
str += data.get(i);
}
mText.setText("results: "+String.valueOf(data.size()));
}
public void onPartialResults(Bundle partialResults)
{
Log.d(TAG, "onPartialResults");
}
public void onEvent(int eventType, Bundle params)
{
Log.d(TAG, "onEvent " + eventType);
}
}
public void onClick(View v) {
if (v.getId() == R.id.btn_speak)
{
Intent intent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
intent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL,RecognizerIntent.LANGUAGE_MODEL_FREE_FORM);
intent.putExtra(RecognizerIntent.EXTRA_CALLING_PACKAGE,"voice.recognition.test");
intent.putExtra(RecognizerIntent.EXTRA_MAX_RESULTS,5);
sr.startListening(intent);
Log.i("111111","11111111");
}
}
}
But it keeps giving me the same results.
I would add that I launched the code on a device (Nexus 4, OS 4.2.2).
Any suggestions on how to deal with this problem ?
Thanks!

I think you are extracting the results from the bundle in the wrong way.
The bundle is a list of the best results, you only need the first one.
Try extracting the results using this code.
public void onResults(Bundle results) {
ArrayList<String> voiceResults =
results.getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION);
if (voiceResults != null) {
String text = voiceResults.get(0);
}
}

Android TTS onUtteranceCompleted callback isn't getting called

I am trying to get the Android TTS API to read my "utterance" and then call the onUtteranceCompleted() listener unsuccessfully. I've registered my TTS object and it returns SUCCESS, so I can't figure out for the life of me why my callback isn't getting called.
I've tried searching for help, but it seems others have difficulty with this too. Am I missing something simple?
Thanks for any help you can offer.
package com.test.mytts;
import java.util.HashMap;
import android.app.Activity;
import android.media.AudioManager;
import android.os.Bundle;
import android.speech.tts.TextToSpeech;
import android.speech.tts.TextToSpeech.OnInitListener;
import android.speech.tts.TextToSpeech.OnUtteranceCompletedListener;
import android.widget.TextView;
import android.widget.Toast;
public class MyTTS extends Activity implements OnInitListener, OnUtteranceCompletedListener
{
TextView tv;
private TextToSpeech _tts;
#Override
public void onCreate(Bundle savedInstanceState)
{
tv = new TextView(this);
tv.setText("MyTTS: ");
super.onCreate(savedInstanceState);
setContentView(tv);
_tts = new TextToSpeech(this, this);
}
#Override
public void onInit(int status)
{
HashMap<String, String> myHashAlarm = new HashMap<String, String>();
myHashAlarm.put(TextToSpeech.Engine.KEY_PARAM_STREAM, String.valueOf(AudioManager.STREAM_NOTIFICATION));
myHashAlarm.put(TextToSpeech.Engine.KEY_PARAM_UTTERANCE_ID, "test");
if (status == TextToSpeech.SUCCESS)
{
Toast.makeText(this, "Trying to speak...", Toast.LENGTH_SHORT).show();
int result = _tts.setOnUtteranceCompletedListener(this);
tv.append(String.valueOf(result));
_tts.setSpeechRate((float) .5);
_tts.speak("Testing one, two, three", TextToSpeech.QUEUE_ADD, myHashAlarm);
}
else
Toast.makeText(this, "Failed to initialize TTS.", Toast.LENGTH_SHORT).show();
}
#Override
public void onUtteranceCompleted(String utteranceId)
{
Toast.makeText(this, "onUtteranceCompleted", Toast.LENGTH_SHORT).show();
}
#Override
public void onDestroy()
{
super.onDestroy();
_tts.shutdown();
}
}

Call the setOnUtteranceCompletedListener inside the onInit function of the tts object.
If you want to make any changes to the UI on the call of the onUtteranceCompleted function, add the code inside a runOnUIThread method.
And do remember to add the Hashmap param value while calling the speak() function
Example :
TextToSpeech tts= new TextToSpeech(context, new OnInitListener() {
#Override
public void onInit(int status) {
mTts.setOnUtteranceCompletedListener(new OnUtteranceCompletedListener() {
#Override
public void onUtteranceCompleted(String utteranceId) {
runOnUiThread(new Runnable() {
#Override
public void run() {
//UI changes
}
});
}
});
}
});
HashMap<String, String> params = new HashMap<String, String>();
params.put(TextToSpeech.Engine.KEY_PARAM_UTTERANCE_ID,"stringId");
tts.speak("Text to Speak",TextToSpeech.QUEUE_FLUSH, params);

I believe that unless you specify an utterance with an id, like:
map.put(TextToSpeech.Engine.KEY_PARAM_UTTERANCE_ID, utteranceid);
your utterance completed method will not be called.
in this case, map is the Hashmap you pass to the engine when you speak.

this will work for you on API Level >=15
import java.util.HashMap;
import java.util.Locale;
import android.app.Activity;
import android.content.Intent;
import android.os.Bundle;
import android.speech.tts.TextToSpeech;
import android.speech.tts.TextToSpeech.OnInitListener;
import android.speech.tts.UtteranceProgressListener;
import android.util.Log;
import android.view.Menu;
import android.view.View;
import android.widget.Button;
import android.widget.EditText;
import android.widget.Toast;
public class MainActivity extends Activity implements OnInitListener{
private static final int CHECK_TTS_DATA = 0X123;
protected static final String TAG = MainActivity.class.getSimpleName();
private TextToSpeech textToSpeech;
private Button buttonSayIt;
private EditText editTextTts;
String tts;
#Override
protected void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
setContentView(R.layout.activity_main);
buttonSayIt=(Button) findViewById(R.id.buttonSayIt);
editTextTts=(EditText) findViewById(R.id.editTextTts);
buttonSayIt.setOnClickListener(new View.OnClickListener() {
#Override
public void onClick(View v) {
tts=editTextTts.getText().toString();
Log.d(TAG, tts);
speach(tts,"you_utterance_id");
}
});
//check for TTs data
Intent checkTtsDataIntent=new Intent();
checkTtsDataIntent.setAction(TextToSpeech.Engine.ACTION_CHECK_TTS_DATA);
startActivityForResult(checkTtsDataIntent, CHECK_TTS_DATA);
}
protected void speach(String tts,String utteranceId) {
HashMap<String, String> params = new HashMap<String, String>();
params.put(TextToSpeech.Engine.KEY_PARAM_UTTERANCE_ID,utteranceId);
textToSpeech.speak(tts,TextToSpeech.QUEUE_FLUSH,params);
}
#Override
public void onInit(int status) {
if(status==TextToSpeech.SUCCESS){
if(textToSpeech.isLanguageAvailable(Locale.US)==TextToSpeech.LANG_AVAILABLE){
textToSpeech.setLanguage(Locale.US);
}
}else if(status==TextToSpeech.ERROR){
Toast.makeText(this, "Sorry Text To Speach faild", Toast.LENGTH_SHORT).show();
}
}
#Override
protected void onActivityResult(int requestCode, int resultCode, Intent data) {
if(requestCode==CHECK_TTS_DATA){
if(resultCode==TextToSpeech.Engine.CHECK_VOICE_DATA_PASS){
textToSpeech=new TextToSpeech(this, this);
textToSpeech.setOnUtteranceProgressListener(utteranceProgressListener);
}else{
Intent installTtsIntent=new Intent();
installTtsIntent.setAction(TextToSpeech.Engine.ACTION_INSTALL_TTS_DATA);
startActivity(installTtsIntent);
}
}
}
UtteranceProgressListener utteranceProgressListener=new UtteranceProgressListener() {
#Override
public void onStart(String utteranceId) {
Log.d(TAG, "onStart ( utteranceId :"+utteranceId+" ) ");
}
#Override
public void onError(String utteranceId) {
Log.d(TAG, "onError ( utteranceId :"+utteranceId+" ) ");
}
#Override
public void onDone(String utteranceId) {
Log.d(TAG, "onDone ( utteranceId :"+utteranceId+" ) ");
}
};
#Override
public boolean onCreateOptionsMenu(Menu menu) {
getMenuInflater().inflate(R.menu.main, menu);
return true;
}
}

in case anybody is still finding it difficult
Code Snippet
textToSpeech=new TextToSpeech(this, new TextToSpeech.OnInitListener() {
#Override
public void onInit(int status) {
if (status==TextToSpeech.SUCCESS){
int result=textToSpeech.setLanguage(Locale.ENGLISH);
if (result==TextToSpeech.LANG_MISSING_DATA||result==TextToSpeech.LANG_NOT_SUPPORTED){
Log.i("TextToSpeech","Language Not Supported");
}
textToSpeech.setOnUtteranceProgressListener(new UtteranceProgressListener() {
#Override
public void onStart(String utteranceId) {
Log.i("TextToSpeech","On Start");
}
#Override
public void onDone(String utteranceId) {
Log.i("TextToSpeech","On Done");
}
#Override
public void onError(String utteranceId) {
Log.i("TextToSpeech","On Error");
}
});
}else {
Log.i("TextToSpeech","Initialization Failed");
}
}
});
if (Build.VERSION.SDK_INT >= Build.VERSION_CODES.LOLLIPOP) {
textToSpeech.speak(text,TextToSpeech.QUEUE_FLUSH,null,TextToSpeech.ACTION_TTS_QUEUE_PROCESSING_COMPLETED);
}