我正在尝试将语音识别内置到我的应用程序中，并且我看到onBeginningOfSpeech和onEndOfSpeech在1秒内被解雇。
另外，当我说完后，语音识别在我给出间隙后立即结束。通常情况下，ASR在停止语音识别之前需要大约3-5秒的等待时间。
即使在手机上的其他应用程序中，此代码实际上也会破坏其余的语音识别功能。
有这样的情况吗？
这就是我的代码的样子。
这是我服务的onCreate方法。我正在使用服务来调用语音识别
@Override
public void onCreate() {
super.onCreate();
createSR();
mSpeechRecognizerIntent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
mSpeechRecognizerIntent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL,
RecognizerIntent.LANGUAGE_MODEL_FREE_FORM);
mSpeechRecognizerIntent.putExtra(RecognizerIntent.EXTRA_PARTIAL_RESULTS, true);
mSpeechRecognizerIntent.putExtra("android.speech.extra.DICTATION_MODE", true);
mSpeechRecognizerIntent.putExtra(RecognizerIntent.EXTRA_CALLING_PACKAGE,
this.getPackageName());
}
这是识别监听器代码。
protected class SpeechRecognitionListener implements RecognitionListener {
private static final String TAG = "SRecognitionListener";
private boolean isUserSpeaking;
private long userSpokeAt=-1;
private long userStoppedSpeakingAt = -1;
private String completeSegment;
private String recognizingSegment;
private ArrayList<String> recognizedSegments;
@Override
public void onBeginningOfSpeech() {
Log.d(TAG, "onBeginingOfSpeech"); //$NON-NLS-1$
}
@Override
public void onBufferReceived(byte[] buffer) {
}
@Override
public void onEndOfSpeech() {
Log.d(TAG, "onEndOfSpeech"); //$NON-NLS-1$
}
@Override
public void onError(int error) {
Log.d(TAG, "onError: " + error);
if (error == SpeechRecognizer.ERROR_NO_MATCH) {
return;
}
mIsListening = false;
Message message = Message.obtain(null, MSG_RECOGNIZER_START_LISTENING);
try {
mServerMessenger.send(message);
} catch (RemoteException e) {
}
Log.d(TAG, "error = " + error); //$NON-NLS-1$
}
@Override
public void onEvent(int eventType, Bundle params) {
}
/* TODO
* There needs to be a boolean variable that would make sure that the translated message from the partialResults would be a fresh message by refreshing the entire data in the bundle data
* Replace the recognizingSegment to have an empty string before doing anything
* */
@Override
public void onPartialResults(Bundle partialResults) {
ArrayList<String> matches = partialResults.getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION);
if (matches != null && matches.size() != 0) {
Log.d(TAG, "onPartialResults: " + matches.get(0));
partialBundleData = partialResults;
String nextPartResult=matches.get(0);
if (!recognizingSegment.equals("")){
String[] nextPartWords = nextPartResult.split(" ");
String[] recWords;
String previousSegments="";
recWords = recognizingSegment.split(" "); //The last recognized segment
if (recognizedSegments.size()>0){
previousSegments=mergeSegments(recognizedSegments);
}
if (nextPartWords.length+2>=recWords.length){ //Most definitely the same segment
Log.d(TAG, "onPartialResults: matching "+recognizingSegment+" with "+nextPartResult);
if (doWordsMatch(recWords,nextPartWords)) { //Since the words match this is probably the same segment
recognizingSegment = nextPartResult;
partialResult = previousSegments + " " + recognizingSegment;
Log.d(TAG, "onPartialResults: Same segment - " + partialResult);
partialResults.putString("PartialSentence", partialResult);
}else{ //Since the words don't match this is probably a new segment
recognizedSegments.add(recognizingSegment);
partialResult=previousSegments+" "+recognizingSegment+" "+nextPartResult;
Log.d(TAG, "onPartialResults: New segment - " + partialResult);
partialResults.putString("PartialSentence",partialResult);
recognizingSegment=nextPartResult;
}
}else{ //This must be a new segment
Log.d(TAG, "onPartialResults: matching "+recognizingSegment+" with "+nextPartResult);
if (!doWordsMatch(recWords, nextPartWords)) { //Since the words don't match this is probably a new segment
recognizedSegments.add(recognizingSegment);
partialResult = previousSegments + " " + recognizingSegment + " " + nextPartResult;
Log.d(TAG, "onPartialResults: New segment - " + partialResult);
partialResults.putString("PartialSentence", partialResult);
recognizingSegment = nextPartResult;
}else{ //Since the words match this is probably the same segment
recognizingSegment = nextPartResult;
partialResult = previousSegments + " " + recognizingSegment;
Log.d(TAG, "onPartialResults: Same segment - " + partialResult);
partialResults.putString("PartialSentence", partialResult);
}
}
}else{
partialResult=nextPartResult;
Log.d(TAG, "onPartialResults: First segment - " + partialResult);
recognizingSegment=nextPartResult;
partialResults.putString("PartialSentence",nextPartResult);
}
Message message = new Message();
message.what = ASRService.MSG_RECOGNIZER_PART_RESULT;
message.setData(partialResults);
sendMessageToClients(message);
} else {
Log.d(TAG, "onPartialResults: No Results");
}
}
private boolean doWordsMatch(String[] phraseA, String[] phraseB){
int noOfWordsToMatch=3;
if (phraseA.length<noOfWordsToMatch){
noOfWordsToMatch=phraseA.length;
}
if (phraseB.length<noOfWordsToMatch){
noOfWordsToMatch=phraseB.length;
}
boolean wordsMatch=false;
int noOfMatchingWords=0;
for (int i=0; i<noOfWordsToMatch; i++){
if (phraseA[i].equals(phraseB[i])){
noOfMatchingWords++;
}
}
Log.d(TAG, "onPartialResults: noOfMatchingWords - "+noOfMatchingWords);
if (noOfMatchingWords>=2 || noOfMatchingWords>=noOfWordsToMatch){
wordsMatch=true;
}
return wordsMatch;
}
private String mergeSegments(ArrayList<String> segments){
StringBuilder mergedSegments=new StringBuilder();
for (String segment: segments){
mergedSegments.append(segment+" ");
}
return mergedSegments.toString().trim();
}
@Override
public void onReadyForSpeech(Bundle params) {
Log.d(TAG, "onReadyForSpeech"); //$NON-NLS-1$
Message message = new Message();
message.what = ASRService.MSG_RECOGNIZER_STARTED_LISTENING;
sendMessageToClients(message);
userSpokeAt=-1;
completeSegment ="";
recognizingSegment="";
recognizedSegments=new ArrayList<>();
}
@Override
public void onResults(Bundle results) {
ArrayList<String> matches = results.getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION);
if (matches != null && matches.size() != 0) {
Log.d(TAG, "onResults: " + matches.get(0));
Message message = new Message();
message.what = ASRService.MSG_RECOGNIZER_RESULT;
message.setData(results);
sendMessageToClients(message);
} else {
Log.d(TAG, "onResults: No Results");
}
cancelSR();
}
@Override
public void onRmsChanged(float rmsdB) {
if (rmsdB > 20) {
if (userSpokeAt==-1) { //The user spoke the first time
partialResultsTimer = new AsyncTask<Void, Void, Void>() {
@Override
protected Void doInBackground(Void... params) {
try {
Thread.sleep(70000); //We wait for a max duration of this time to cancel the speech recognition because the service automatically times out anyway.
partialResultsTimer=null;
cancelSR();
} catch (InterruptedException e) {
}
return null;
}
}.execute();
}
userSpokeAt = System.currentTimeMillis();
if (!isUserSpeaking) {
Log.d(TAG, "User started speaking");
isUserSpeaking = true;
if (userStoppedSpeakingAt != -1) {
long gap = userSpokeAt - userStoppedSpeakingAt;
Log.d(TAG, "User spoke after " + gap + " millis");
}
userStoppedSpeakingAt = -1;
if (timeoutTaskRunner != null) {
Log.d(TAG, "Speech Recognition timer canceling");
timeoutTaskRunner.cancel();
timerRunning = false;
}
Message message = new Message();
message.what = ASRService.MSG_RECOGNIZER_USER_SPEAKING_STATE_CHANGED;
message.arg1 = 1; //1 means true
sendMessageToClients(message);
}
} else if (isUserSpeaking) {
long currentTimeMillis = System.currentTimeMillis();
if (currentTimeMillis - userSpokeAt > 1700) {
isUserSpeaking = false;
Log.d(TAG, "User isn't speaking after: " + (currentTimeMillis - userSpokeAt));
userStoppedSpeakingAt = currentTimeMillis;
startTimer();
Message message = new Message();
message.what = ASRService.MSG_RECOGNIZER_USER_SPEAKING_STATE_CHANGED;
message.arg1 = 0; //0 means false
sendMessageToClients(message);
}
}
}
}
@Override
public IBinder onBind(Intent arg0) {
Log.d("ASRService", "onBind"); //$NON-NLS-1$
return mServerMessenger.getBinder();
} }