将音频与歌词同步

Question

我正在尝试同步音频文件和歌词文件（String格式）。在SO上关注了很多帖子后，我尝试使用Speech To Text从音频中获取文本。但它不听音频，它等待演讲。并且歌词文件需要根据歌曲转换为SRT文件。以下怎么可能？

1. 使用TTS收听音频文件？这是正确的方法吗？
2. 如何将歌词文件（字符串格式）转换为SRT文件？

我们将非常感谢任何建议/指导。 下面的代码等着我说一些话。但我需要它来听音频文件播放。 我到目前为止已尝试过的代码：

@Override
protected void onCreate(Bundle savedInstanceState) {
    super.onCreate(savedInstanceState);
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)
            {
                String mError=null;
                Intent intent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
                intent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL,
                        RecognizerIntent.LANGUAGE_MODEL_FREE_FORM);


                 switch (error) {
                 case SpeechRecognizer.ERROR_NETWORK_TIMEOUT:                
                     mError = " network timeout"; 
                     sr.startListening(intent);
                     break;
                 case SpeechRecognizer.ERROR_NETWORK: 
                     mError = " network" ;
                     //toast("Please check data bundle or network settings");
                     return;
                 case SpeechRecognizer.ERROR_AUDIO: 
                     mError = " audio"; 
                     break;
                 case SpeechRecognizer.ERROR_SERVER: 
                     mError = " server"; 
                     sr.startListening(intent);

                     break;
                 case SpeechRecognizer.ERROR_CLIENT: 
                     mError = " client"; 
                     break;
                 case SpeechRecognizer.ERROR_SPEECH_TIMEOUT: 
                     mError = " speech time out" ; 
                     break;
                 case SpeechRecognizer.ERROR_NO_MATCH: 
                     mError = " no match" ; 
                     sr.startListening(intent);


                     break;
                 case SpeechRecognizer.ERROR_RECOGNIZER_BUSY: 
                     mError = " recogniser busy" ; 
                     break;
                 case SpeechRecognizer.ERROR_INSUFFICIENT_PERMISSIONS: 
                     mError = " insufficient permissions" ; 
                     break;

                 }    

                Log.d(TAG,  "error " +  mError);

            }
            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);
                     }

            }
            public void onPartialResults(Bundle partialResults)
            {
                     Log.d(TAG, "onPartialResults");
            }
            public void onEvent(int eventType, Bundle params)
            {
                     Log.d(TAG, "onEvent " + eventType);
            }
   }

public void onSongPicked()
{
Intent intent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
        intent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL,
                RecognizerIntent.LANGUAGE_MODEL_FREE_FORM);

        sr.startListening(intent);}