适用于Android的Google云语音API

Question

目前，我正在致力于一个项目，我必须使用Google Cloud Speech Api和TextToSpeech。我试着用RecognizerIntent解决问题，但我想尝试一下Cloud Speech。

会很棒的一些教程材料或指南，我检查了示例应用程序 ，但我正在寻找教程，指导任何可以解释的东西。

这是我的工作与TTS和RecognizerIntent。

private TextToSpeech tts; 
private TextToSpeech secondTTS; 
private TextView speechInputTextView,correctAnswerTextView,wrongAnswerTextView,currentQuestionTextView; 
private ArrayList<String> correctAnswersArrayList, questionArrayList, sayCorrectArrayList, sayWrongArrayList ,toSay ,toASk; 
private MediaPlayer mediaPlayer; 
private DBHelper dbHelper; 
private SQLiteDatabase sqlDB; 
private int correctACount,wrongACount,currentQuestion, Unit; 
private boolean isStarted; 
private String currentLanguage ; 
private static int TOTAL_QUESITONS; 
private final static int REQ_CODE_SPEECH_INPUT = 100; 
private final static String PAUSE_COMMAND = "pos"; 
private final static String STOP_COMMAND = "stop"; 
private final static String RESTART_COMMNAD = "restart"; 
private final static String REPEAT_COMMAND = "repeat"; 
private final static String EXIT_COMMAND = "exit"; 
@Override 
protected void onCreate(Bundle savedInstanceState) { 
    super.onCreate(savedInstanceState); 
    setContentView(R.layout.activity_unit); 
    isStarted = true; 
    mediaPlayer = MediaPlayer.create(getApplicationContext(), R.raw.unitonemp3); 
    currentQuestion = 0; 
    speechInputTextView = (TextView) findViewById(R.id.speechInput); 
    correctAnswerTextView = (TextView) findViewById(R.id.correctAnswers_TextView); 
    currentQuestionTextView = (TextView) findViewById(R.id.currentQuestion_TextView); 
    wrongAnswerTextView = (TextView) findViewById(R.id.wrongAnswer_TextView); 

    Unit = 1; 
    currentLanguage = getIntent().getBundleExtra("resultBundle").getString("language"); 


    Button next = (Button) findViewById(R.id.nextButton); 
    Button changeUnitButton = (Button) findViewById(R.id.changeUnitButton); 
    Button playButton = (Button) findViewById(R.id.playButton); 
    Button pauseButton = (Button) findViewById(R.id.pauseButton); 

    playButton.setOnClickListener(new View.OnClickListener() { 
     @Override 
     public void onClick(View v) { 
      startSayWithID(questionArrayList.get(currentQuestion), 1000, "say"); 
     } 
    }); 

    pauseButton.setOnClickListener(new View.OnClickListener() { 
     @Override 
     public void onClick(View v) { 
      tts.stop(); 
      secondTTS.stop(); 
      Intent pauseI = new Intent(UnitActivity.this, PauseActivity.class); 
      Bundle resultBundle = new Bundle(); 
      resultBundle.putInt("npc", currentQuestion); 
      pauseI.putExtra("resultBundle", resultBundle); 
      startActivity(pauseI); 

     } 
    }); 

    tts = new TextToSpeech(this, this); 
    secondTTS = new TextToSpeech(this, this); 


changeUnitButton.setOnClickListener(new View.OnClickListener() { 
     @Override 
     public void onClick(View v) { 

      secondTTS.stop(); 
      tts.stop(); 
      Unit ++; 
      mediaPlayer.start(); 

     } 
    }); 



    Bundle extras = getIntent().getExtras(); 
    if (extras != null) { 
     currentQuestion = getIntent().getBundleExtra("resultBundle").getInt("npc"); 

    } 

    ImageView micButton = (ImageView) findViewById(R.id.micButton); 
    micButton.setOnClickListener(new View.OnClickListener() { 
     @Override 
     public void onClick(View v) { 
      if (!tts.isSpeaking()) { 
       currentQuestion = 13; 
       startSayWithID(questionArrayList.get(currentQuestion), 1000, "questionID"); 
      } 
     } 

    }); 

    String[] sayCorrectList = getResources().getStringArray(R.array.sayCorrect); 
    String[] sayWrongList = getResources().getStringArray(R.array.satWrong); 

    String[] listToSay = getResources().getStringArray(R.array.toSay); 
    String[] listToAsk = getResources().getStringArray(R.array.toAsk); 

    toSay = new ArrayList<>(Arrays.asList(listToSay)); 
    toASk = new ArrayList<>(Arrays.asList(listToAsk)); 
    questionArrayList = new ArrayList<>(); 
    correctAnswersArrayList = new ArrayList<>(); 


    addGerCorrect(); 
    addEngQuestions(); 


    sayCorrectArrayList = new ArrayList<>(Arrays.asList(sayCorrectList)); 
    sayWrongArrayList = new ArrayList<>(Arrays.asList(sayWrongList)); 


    TOTAL_QUESITONS = questionArrayList.size(); 
    mediaPlayer.start(); 

    mediaPlayer.setOnCompletionListener(new MediaPlayer.OnCompletionListener() { 
     @Override 
     public void onCompletion(MediaPlayer mp) { 

      startSayWithID("Welcome",1000,"instruction"); 
     } 
    }); 



    next.setOnClickListener(new View.OnClickListener() { 
     @Override 
     public void onClick(View v) { 

      for(int i = 0 ; i< questionArrayList.size();i++){ 
       Log.d(" question List "," item :"+"pisition "+i+ "" +questionArrayList.get(i)); 

      } 
      currentQuestion++; 
      tts.stop(); 
      secondTTS.stop(); 

      startSayWithID("",1000,"instruction"); 
     } 

    }); 

    tts.setOnUtteranceProgressListener(new UtteranceProgressListener() { 

     @Override 
     public void onStart(String utteranceId) { 

     } 

     @Override 
     public void onDone(final String utteranceId) { 
      runOnUiThread(new Runnable() { 
       @Override 
       public void run() { 


        if (utteranceId.contains("say")) { 


         if (correctAnswersArrayList.get(currentQuestion).contains("tensa23")) { 
          startSayWithID(questionArrayList.get(currentQuestion), 1000, "say"); 
          currentQuestion++; 
          Log.d("Current ", "current Question" + currentQuestion + "" + correctAnswersArrayList.get(currentQuestion)); 
         }else 
          startSayWithID(questionArrayList.get(currentQuestion), 1000, "question"); 
        } 

        if (utteranceId.contains("instruction")) { 

         if (correctAnswersArrayList.get(currentQuestion).contains("tensa23")) { 
          startSayWithID(questionArrayList.get(currentQuestion), 1000, "say"); 
          currentQuestion++; 
          Log.d("Current ","current Question"+currentQuestion +""+correctAnswersArrayList.get(currentQuestion)); 
         } else if (questionArrayList.get(currentQuestion).contains("?")) { 
          startSayWithID(toASk.get(new Random().nextInt(toASk.size())), 1000, "say"); 

         } else { 
          startSayWithID(toSay.get(new Random().nextInt(toSay.size())), 1000, "say"); 
         } 
        } 


        if (utteranceId.contains("question")) { 

         if(questionArrayList.get(currentQuestion).contains("?")){ 
          startSayWithID("in Spanish you ask",1000,"german"); 
         }else{ 
          startSayWithID("In Spanish you say",1000,"german"); 
         } 
        } 


        if (utteranceId.contains("german")) { 
         secondTTS.speak(correctAnswersArrayList.get(currentQuestion),TextToSpeech.QUEUE_FLUSH,null,"ask"); 
        } 
        if(utteranceId.contains("ask")){ 
         startAsk(1000); 
        } 


       } 

      }); 
     } 


     @Override 
     public void onError(String utteranceId) { 

     } 

    }); 

    secondTTS.setOnUtteranceProgressListener(new UtteranceProgressListener() { 
     @Override 
     public void onStart(String utteranceId) { 

     } 

     @Override 
     public void onDone(final String utteranceId) { 
      runOnUiThread(new Runnable() { 
       @Override 
       public void run() { 
        if(utteranceId.contains("ask")){ 
         startAsk(1000); 
        } 
       } 
      }); 

     } 

     @Override 
     public void onError(String utteranceId) { 

     } 
    }); 




    // end of MainActivity 
} 


private void promptSpeechInput() { 
    Intent prompIntent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH); 
    prompIntent.putExtra(RecognizerIntent.EXTRA_LANGUAGE, "es-ES"); 
    prompIntent.putExtra(RecognizerIntent.EXTRA_PROMPT, "How do you say \n" +questionArrayList.get(currentQuestion)); 
    try { 
     startActivityForResult(prompIntent, REQ_CODE_SPEECH_INPUT); 
    } catch (ActivityNotFoundException a) { 

     makeText(getApplicationContext(), "speech not supported", Toast.LENGTH_SHORT).show(); 
    } 
} 

@Override 
public void onInit(int status) { 
    if (status == TextToSpeech.SUCCESS) { 
     tts.setLanguage(Locale.US); 

     switch (currentLanguage){ 
      case "Spanish" : 
       secondTTS.setLanguage(new Locale("es","Es")); 
       break; 
      case "Italian" : 
       secondTTS.setLanguage(Locale.ITALY); 
       break; 
      case "German" : 
       secondTTS.setLanguage(Locale.GERMAN); 
       break; 
      case "French" : 
       secondTTS.setLanguage(Locale.FRENCH); 
       break; 
     } 
    } 

} 

protected void onActivityResult(int requestCode, int resultCode, Intent data) { 
    super.onActivityResult(requestCode, resultCode, data); 
    switch (requestCode) { 
     case REQ_CODE_SPEECH_INPUT: { 
      if (resultCode == RESULT_OK && null != data) { 
       ArrayList<String> result = data 
         .getStringArrayListExtra(RecognizerIntent.EXTRA_RESULTS); 

       speechInputTextView.setText(result.get(0)); 
      } 
     } 
     String inputSpeechToString = speechInputTextView.getText().toString().toLowerCase(); 



     if (currentQuestion < TOTAL_QUESITONS && inputSpeechToString.contains(correctAnswersArrayList.get(currentQuestion))) { 
      currentQuestion++; 
      correctACount++; 

      correctAnswerTextView.setText(String.valueOf(correctACount)); 
      currentQuestionTextView.setText(String.valueOf(currentQuestion)); 


      Log.d("Onactivity ", "CurrentQ = " + currentQuestion); 
      startSayWithID(sayCorrectArrayList.get(new Random().nextInt(sayCorrectArrayList.size())), 1000, "instruction"); 


     } else if (inputSpeechToString.contains(STOP_COMMAND)) { 
      Intent stopIntent = new Intent(UnitActivity.this, PauseActivity.class); 
      Bundle resultBundle = new Bundle(); 
      resultBundle.putBoolean("isStarted", isStarted); 
      stopIntent.putExtra("resultBundle", resultBundle); 
      startActivity(stopIntent); 

     } else if (inputSpeechToString.contains(PAUSE_COMMAND)) { 
      Intent pauseI = new Intent(UnitActivity.this, PauseActivity.class); 
      Bundle resultBundle = new Bundle(); 
      resultBundle.putInt("npc", currentQuestion); 
      pauseI.putExtra("resultBundle", resultBundle); 
      startActivity(pauseI); 
     } else if (inputSpeechToString.contains(RESTART_COMMNAD)) { 
      currentQuestion = 0; 
      startSayWithID("Restarted", 1000, "say"); 
     } else if (inputSpeechToString.contains(REPEAT_COMMAND)) { 
      startSayWithID(questionArrayList.get(currentQuestion), 1000, "question"); 
     } else if (inputSpeechToString.contains(EXIT_COMMAND)) { 
      Intent homeIntent = new Intent(Intent.ACTION_MAIN); 
      homeIntent.addCategory(Intent.CATEGORY_HOME); 
      homeIntent.setFlags(Intent.FLAG_ACTIVITY_CLEAR_TOP); 
      startActivity(homeIntent); 


     } else { 
      startSayWithID(sayWrongArrayList.get(new Random().nextInt(sayWrongArrayList.size())), 1000, "instruction"); 
      wrongACount++; 
      wrongAnswerTextView.setText(String.valueOf(wrongACount)); 
      Log.d("Onactivity ", "CORRECT = " + correctAnswersArrayList.get(currentQuestion)); 
      Log.d("Onactivity ", "You said : " + inputSpeechToString); 
     } 


    } 
} 


private void addEngQuestions() { 
    dbHelper = new DBHelper(this); 
    sqlDB = dbHelper.getReadableDatabase(); 
    String queryEngQuestion = "SELECT English FROM " +currentLanguage+ " WHERE " + "Unit = " +Unit+ " ORDER BY Unit ASC"; 
    Cursor cursor = sqlDB.rawQuery(queryEngQuestion, null); 
    try { 
     cursor.moveToFirst(); 
     while (!cursor.isAfterLast()) { 
      questionArrayList.add(cursor.getString(cursor.getColumnIndex("English"))); 

      cursor.moveToNext(); 

     } 
    } finally { 
     cursor.close(); 
    } 
    Log.d("Line 255", " English Arraylist" + questionArrayList.size()); 
} 


private void addGerCorrect() { 
    dbHelper = new DBHelper(this); 
    sqlDB = dbHelper.getReadableDatabase(); 
    String queryGerCOrrect = "SELECT "+ currentLanguage +" FROM "+ currentLanguage + " WHERE "+ "Unit = "+Unit+ " ORDER BY Unit ASC"; 
    Cursor cursor2 = sqlDB.rawQuery(queryGerCOrrect, null); 
    try { 
     cursor2.moveToFirst(); 
     while (!cursor2.isAfterLast()) { 
      correctAnswersArrayList.add(cursor2.getString(cursor2.getColumnIndex(currentLanguage)) 
        .replaceAll("\\p{P}", "").toLowerCase()); 

      cursor2.moveToNext(); 
     } 
    } finally { 
     cursor2.close(); 
    } 
} 


private void startSayWithID(final String text, int mSeconds, final String ID) { 
    final Handler handler = new Handler(); 
    handler.postDelayed(new Runnable() { 
     @Override 
     public void run() { 
      tts.speak(text, TextToSpeech.QUEUE_FLUSH, null, ID); 
     } 
    }, mSeconds); 
} 

private void startAsk(int seconds) { 
    final Handler handler = new Handler(); 
    handler.postDelayed(new Runnable() { 
     @Override 
     public void run() { 

      promptSpeechInput(); 

     } 
    }, seconds); 
} 

@Override 
protected void onDestroy() { 
    if (mediaPlayer != null) { 
     mediaPlayer.stop(); 
     mediaPlayer.release(); 
    } 

    if (tts != null) { 
     tts.stop(); 
     tts.shutdown(); 
    } 
    if (secondTTS != null) { 
     secondTTS.stop(); 
     secondTTS.shutdown(); 
    } 
    super.onDestroy(); 
} 

Answer 1

在Android上设置Google语音云不是一个简单的1,2,3过程，但我会给你一些指导。

1. 从这里下载示例项目，使用语音示例。 https://github.com/GoogleCloudPlatform/android-docs-samples/tree/master/speech/Speech
2. 设置一个谷歌的云计算项目，使语音API，并将其链接到 您的Gmail帐户的结算（你得到免费的语音识别 每月60分钟）。
3. 生成验证json，并将其放入示例项目的 “原始”文件夹中。
4. 在您的计算机上设置Google云并获取访问令牌。 在您的SpeechService.java类中插入该访问令牌。

*文档上的步骤3和4： https://cloud.google.com/speech/docs/getting-started

*如果你试图模仿的样本项目到自己的项目时遇到问题，检查： Cannot import com.google.cloud.speech.v1.SpeechGrpc in Android

的具体步骤如果遇到特定的麻烦让我知道，我甚至都不记得他们。