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);
}
}
Related
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);
}
package com.example.hp.check2;
import android.content.Intent;
import android.speech.RecognitionListener;
import android.speech.RecognizerIntent;
import android.speech.SpeechRecognizer;
import android.support.v7.app.AppCompatActivity;
import android.os.Bundle;
import android.view.View;
import android.widget.Button;
import android.widget.TextView;
import android.widget.Toast;
import java.util.ArrayList;
public class MainActivity extends AppCompatActivity {
ArrayList data;
TextView tv;
Button speakButton;
public SpeechRecognizer sr;
#Override
protected void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
setContentView(R.layout.activity_main);
speakButton = (Button) findViewById(R.id.btn_speak);
sr = SpeechRecognizer.createSpeechRecognizer(this);
sr.setRecognitionListener(new listener());
tv=(TextView)findViewById(R.id.textView);
data=new ArrayList();
}
class listener implements RecognitionListener
{
#Override
public void onReadyForSpeech(Bundle params) {
Toast.makeText(MainActivity.this, "onReadyForSpeech", Toast.LENGTH_SHORT).show();
}
#Override
public void onBeginningOfSpeech() {
Toast.makeText(MainActivity.this, "onBeginningOfSpeech", Toast.LENGTH_SHORT).show();
}
#Override
public void onRmsChanged(float rmsdB) {
Toast.makeText(MainActivity.this, "onRmsChanged", Toast.LENGTH_SHORT).show();
}
#Override
public void onBufferReceived(byte[] buffer) {
Toast.makeText(MainActivity.this, "onbufferreceived", Toast.LENGTH_SHORT).show();
}
#Override
public void onEndOfSpeech() {
Toast.makeText(MainActivity.this, "onEndOfSpeech", Toast.LENGTH_SHORT).show();
}
#Override
public void onError(int error) {
Toast.makeText(MainActivity.this, "onError", Toast.LENGTH_SHORT).show();
}
#Override
public void onResults(Bundle results) {
String str = new String();
data = results.getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION);
for (int i = 0; i < data.size()+10; i++)
{
str += data.get(i)+"S";
}
tv.setText(str);
}
#Override
public void onPartialResults(Bundle partialResults) {
Toast.makeText(MainActivity.this, "onPartialReults", Toast.LENGTH_SHORT).show();
}
#Override
public void onEvent(int eventType, Bundle params) {
Toast.makeText(MainActivity.this, "onEvent", Toast.LENGTH_SHORT).show();
}
}
public void onClick(View v) {
if (v.getId() == R.id.btn_speak)
{
sr.startListening(new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH));
}
}
}
When I am running the code,I am just getting the toast of onRmsChanged and nothing else and it continues till I close the application.And there is no method change when I try to speak as there is no new Toast appearing on the screen.I have read about onRmsChanged on internet but didn't get it much.I have granted the permission of microphone but still the problem occurs.Any idea what is going on?
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.
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.
I used method Intent and SpeechRecognizer but it very slow translate from speech to text, it took than 30s but something it faster about 3s. How to make it faster same same voice search of google? thanks you reading!
This is example code:
Method Intent
package com.example.android.apis.app;
import com.example.android.apis.R;
import android.app.Activity;
import android.content.Intent;
import android.content.pm.PackageManager;
import android.content.pm.ResolveInfo;
import android.os.Bundle;
import android.speech.RecognizerIntent;
import android.view.View;
import android.view.View.OnClickListener;
import android.widget.ArrayAdapter;
import android.widget.Button;
import android.widget.ListView;
import java.util.ArrayList;
import java.util.List;
/**
* Sample code that invokes the speech recognition intent API.
*/
public class VoiceRecognition extends Activity implements OnClickListener {
private static final int VOICE_RECOGNITION_REQUEST_CODE = 1234;
private ListView mList;
/**
* Called with the activity is first created.
*/
#Override
public void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
// Inflate our UI from its XML layout description.
setContentView(R.layout.voice_recognition);
// Get display items for later interaction
Button speakButton = (Button) findViewById(R.id.btn_speak);
mList = (ListView) findViewById(R.id.list);
// Check to see if a recognition activity is present
PackageManager pm = getPackageManager();
List<ResolveInfo> activities = pm.queryIntentActivities(
new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH), 0);
if (activities.size() != 0) {
speakButton.setOnClickListener(this);
} else {
speakButton.setEnabled(false);
speakButton.setText("Recognizer not present");
}
}
/**
* Handle the click on the start recognition button.
*/
public void onClick(View v) {
if (v.getId() == R.id.btn_speak) {
startVoiceRecognitionActivity();
}
}
/**
* Fire an intent to start the speech recognition activity.
*/
private void startVoiceRecognitionActivity() {
Intent intent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
intent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL,
RecognizerIntent.LANGUAGE_MODEL_FREE_FORM);
intent.putExtra(RecognizerIntent.EXTRA_PROMPT, "Speech recognition demo");
startActivityForResult(intent, VOICE_RECOGNITION_REQUEST_CODE);
}
/**
* Handle the results from the recognition activity.
*/
#Override
protected void onActivityResult(int requestCode, int resultCode, Intent data) {
if (requestCode == VOICE_RECOGNITION_REQUEST_CODE && resultCode == RESULT_OK) {
// Fill the list view with the strings the recognizer thought it could have heard
ArrayList<String> matches = data.getStringArrayListExtra(
RecognizerIntent.EXTRA_RESULTS);
mList.setAdapter(new ArrayAdapter<String>(this, android.R.layout.simple_list_item_1,
matches));
}
super.onActivityResult(requestCode, resultCode, data);
}
}
Method SpeechRecognizer
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");
}
}
}