我正在使用 android 语音识别并编写了一些代码来识别所说的话。请看下面的代码。
import java.util.ArrayList;
import java.util.Arrays;
import java.util.LinkedList;
import java.util.List;
import android.speech.RecognitionListener;
import android.speech.RecognizerIntent;
import android.speech.SpeechRecognizer;
import android.app.Activity;
import android.content.Intent;
import android.os.Bundle;
import android.speech.tts.TextToSpeech;
import android.text.Html;
import android.util.Log;
import android.view.View;
import android.widget.AdapterView;
import android.widget.ArrayAdapter;
import android.widget.CompoundButton;
import android.widget.CompoundButton.OnCheckedChangeListener;
import android.widget.ListView;
import android.widget.ProgressBar;
import android.widget.TextView;
import android.widget.Toast;
import android.widget.ToggleButton;
public class MainActivity extends Activity {
private TextView returnedText;
private ToggleButton toggleButton;
private ProgressBar progressBar;
private SpeechRecognizer speech = null;
private Intent recognizerIntent;
private ListView wordList;
private String LOG_TAG = "VoiceRecognitionActivity";
private List<String> previousInterim;
private diff_match_patch diff;
private String display = "test";
private List<String>adapterList = new ArrayList<String>();
ArrayAdapter<String> adapter;
@Override
protected void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
setContentView(R.layout.activity_main);
returnedText = (TextView) findViewById(R.id.textView1);
progressBar = (ProgressBar) findViewById(R.id.progressBar1);
toggleButton = (ToggleButton) findViewById(R.id.toggleButton1);
wordList = (ListView)findViewById(R.id.word_list);
adapter = new ArrayAdapter<String>(this,android.R.layout.simple_list_item_checked, adapterList);
adapter.setNotifyOnChange(true);
wordList.setAdapter(adapter);
progressBar.setVisibility(View.INVISIBLE);
// createRecog();
speech = SpeechRecognizer.createSpeechRecognizer(getApplicationContext());
toggleButton.setOnCheckedChangeListener(new ButtonListener());
}
private class ButtonListener implements OnCheckedChangeListener, Runnable
{
boolean isChecked;
@Override
public void onCheckedChanged(CompoundButton buttonView, boolean isChecked) {
this.isChecked = isChecked;
this.run();
}
@Override
public void run() {
if (isChecked) {
speech.stopListening();
speech.cancel();
speech.destroy();
createRecog();
progressBar.setVisibility(View.VISIBLE);
progressBar.setIndeterminate(true);
speech.startListening(recognizerIntent);
adapter.clear();
returnedText.setText("");
} else {
progressBar.setIndeterminate(false);
progressBar.setVisibility(View.INVISIBLE);
speech.stopListening();
}
}
}
private class RecognitionListenerClass implements RecognitionListener
{
@Override
public void onBeginningOfSpeech() {
Log.i(LOG_TAG, "onBeginningOfSpeech");
progressBar.setIndeterminate(false);
progressBar.setMax(10);
wordList.computeScroll();
}
@Override
public void onBufferReceived(byte[] buffer) {
Log.i(LOG_TAG, "onBufferReceived: " + buffer);
}
@Override
public void onEndOfSpeech() {
Log.i(LOG_TAG, "onEndOfSpeech");
progressBar.setIndeterminate(true);
toggleButton.setChecked(false);
}
@Override
public void onError(int errorCode) {
String errorMessage = getErrorText(errorCode);
Log.d(LOG_TAG, "FAILED " + errorMessage);
returnedText.setText(errorMessage);
toggleButton.setChecked(false);
// speech = null;
toggleButton.performClick();
}
@Override
public void onEvent(int arg0, Bundle arg1) {
Log.i(LOG_TAG, "onEvent");
}
@Override
public void onPartialResults(Bundle arg0) {
Log.i(LOG_TAG, "onPartialResults");
final ArrayList<String> matches = arg0.getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION);
final float[] scores = arg0.getFloatArray(SpeechRecognizer.CONFIDENCE_SCORES);
receiveWhatWasHeard(matches, scores);
}
@Override
public void onReadyForSpeech(Bundle arg0) {
Log.i(LOG_TAG, "onReadyForSpeech");
}
@Override
public void onResults(Bundle results) {
}
@Override
public void onRmsChanged(float rmsdB) {
Log.i(LOG_TAG, "onRmsChanged: " + rmsdB);
progressBar.setProgress((int) rmsdB);
}
}
private void receiveWhatWasHeard(ArrayList<String> matches, float[] scores) {
Log.i(LOG_TAG, matches.get(0));
returnedText.setText(matches.get(0));
}
private void createRecog()
{
speech = SpeechRecognizer.createSpeechRecognizer(this);
speech.setRecognitionListener(new RecognitionListenerClass());
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);
recognizerIntent.putExtra("android.speech.extra.DICTATION_MODE", true);
recognizerIntent.putExtra(RecognizerIntent.EXTRA_PARTIAL_RESULTS, true);
}
@Override
public void onResume() {
super.onResume();
}
@Override
protected void onPause() {
super.onPause();
}
public String getErrorText(int errorCode) {
String message;
switch (errorCode) {
case SpeechRecognizer.ERROR_AUDIO:
message = "Audio recording error";
break;
case SpeechRecognizer.ERROR_CLIENT:
message = "Client side error";
break;
case SpeechRecognizer.ERROR_INSUFFICIENT_PERMISSIONS:
message = "Insufficient permissions";
break;
case SpeechRecognizer.ERROR_NETWORK:
message = "Network error";
break;
case SpeechRecognizer.ERROR_NETWORK_TIMEOUT:
message = "Network timeout";
break;
case SpeechRecognizer.ERROR_NO_MATCH:
message = "No match";
break;
case SpeechRecognizer.ERROR_RECOGNIZER_BUSY:
message = "RecognitionService busy";
break;
case SpeechRecognizer.ERROR_SERVER:
message = "error from server";
break;
case SpeechRecognizer.ERROR_SPEECH_TIMEOUT:
message = "No speech input";
break;
default:
message = "Didn't understand, please try again.";
break;
}
return message;
}
}
但是我需要连续运行它，但我一直没能做到。在语音结束时重新启动识别可能是个好主意，但它会发出很小的噪音，并且需要 1-3 秒才能加载，这意味着，一些口语单词将会丢失。
是的，我知道谷歌已经提到他们的系统不是为了连续识别；但是之前有几个人做过解决方法。不幸的是，这些变通办法现在似乎不起作用，因为它们是用非常古老的 API 编写的。如果旧版本有可能，那么新版本当然更有可能。
那么，关于如何实现这个连续识别任务有什么想法吗？我正在使用 API 15。
最佳答案
阅读here背景
this demo是连续的，并使用 pultz 博客评论流中提到的 chromium 源
全双工谷歌 API 工作正常 in android . AFAIK，它仍然受到速率限制，因此在生产应用程序中毫无用处。
谷歌全双工 stdout sample使用 curl cli
IBM watson 拥有支持连续模式的全双工和生产就绪 API。您将不得不深入了解文档详细信息，但一般的 cli 示例是 here
参见 continuous here在沃森 API 上
关于java - 没有超时的Android语音识别？，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/34253862/