[Java] STT (Speech-to-Text)

구글  STT  (Speech-to-Text)

---

AndroidManifest.xml

 <uses-permission android:name="android.permission.INTERNET" />
 <uses-permission android:name="android.permission.RECORD_AUDIO" />

 

 

 

 

 

 

 

activity_main.xml

<?xml version="1.0" encoding="utf-8"?>
<androidx.constraintlayout.widget.ConstraintLayout
    xmlns:android="http://schemas.android.com/apk/res/android"
    xmlns:app="http://schemas.android.com/apk/res-auto"
    xmlns:tools="http://schemas.android.com/tools"
    android:layout_width="match_parent"
    android:layout_height="match_parent"
    tools:context=".MainActivity">

    <TextView
        android:id="@+id/tvResult"
        android:layout_width="wrap_content"
        android:layout_height="wrap_content"
        android:text="This is TextView Result"
        android:textSize="26dp"
        app:layout_constraintTop_toTopOf="parent"
        app:layout_constraintLeft_toLeftOf="parent"
        app:layout_constraintRight_toRightOf="parent"
        app:layout_constraintBottom_toBottomOf="parent"/>

    <Button
        android:id="@+id/btnStart"
        android:layout_width="150dp"
        android:layout_height="60dp"
        android:textAllCaps="false"
        android:text="start speech"
        android:textSize="20dp"
        app:layout_constraintTop_toBottomOf="@+id/tvResult"
        app:layout_constraintLeft_toLeftOf="parent"
        app:layout_constraintRight_toRightOf="parent"
        app:layout_constraintBottom_toBottomOf="parent"
        app:layout_constraintVertical_bias="0.1"/>

</androidx.constraintlayout.widget.ConstraintLayout>

activity_main.xml

 

 

 

 

 

MainActivity.java

package com.jwsoft.javaproject;

import androidx.appcompat.app.AppCompatActivity;
import androidx.core.app.ActivityCompat;
import androidx.core.content.ContextCompat;

import android.Manifest;
import android.content.Intent;
import android.content.pm.PackageManager;
import android.os.Build;
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 android.widget.Toast;

import java.util.ArrayList;

public class MainActivity extends AppCompatActivity {

    private SpeechRecognizer speechRecognizer;
    private RecognitionListener recognitionListener;

    TextView tvResult;
    Button btnStart;

    Intent intent;

    @Override
    protected void onCreate(Bundle savedInstanceState) {
        super.onCreate(savedInstanceState);
        setContentView(R.layout.activity_main);

        tvResult = findViewById(R.id.tvResult);
        btnStart = findViewById(R.id.btnStart);

        requestPermission();
        setListener();

        intent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
        intent.putExtra(RecognizerIntent.EXTRA_CALLING_PACKAGE, getPackageName());
        intent.putExtra(RecognizerIntent.EXTRA_LANGUAGE, "ko-KR");

        btnStart.setOnClickListener(new View.OnClickListener() {
            @Override
            public void onClick(View v) {
                speechRecognizer = SpeechRecognizer.createSpeechRecognizer(getApplicationContext());
                speechRecognizer.setRecognitionListener(recognitionListener);
                speechRecognizer.startListening(intent);
            }
        });

    }


    private void requestPermission() {
        if (Build.VERSION.SDK_INT >= 23 && ContextCompat.checkSelfPermission(this,
                Manifest.permission.RECORD_AUDIO) != PackageManager.PERMISSION_GRANTED) {

            // 거부해도 계속 노출됨. ("다시 묻지 않음" 체크 시 노출 안됨.)
            // 허용은 한 번만 승인되면 그 다음부터 자동으로 허용됨.
            ActivityCompat.requestPermissions(this,
                    new String[] {Manifest.permission.RECORD_AUDIO}, 0);
        }
    }


    private void setListener() {
        recognitionListener = new RecognitionListener() {
            @Override
            public void onReadyForSpeech(Bundle params) {
                Toast.makeText(getApplicationContext(), "음성인식 시작", Toast.LENGTH_SHORT).show();
            }

            @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) {
                String message;

                switch (error) {
                    case SpeechRecognizer.ERROR_AUDIO:
                        message = "오디오 에러";
                        break;

                    case SpeechRecognizer.ERROR_CLIENT:
                        message = "클라이언트 에러";
                        break;

                    case SpeechRecognizer.ERROR_INSUFFICIENT_PERMISSIONS:
                        message = "퍼미션 에러";
                        break;

                    case SpeechRecognizer.ERROR_NETWORK:
                        message = "네트워크 에러";
                        break;

                    case SpeechRecognizer.ERROR_NETWORK_TIMEOUT:
                        message = "네트워크 타임아웃";
                        break;

                    case SpeechRecognizer.ERROR_NO_MATCH:
                        message = "찾을 수 없음";
                        break;

                    case SpeechRecognizer.ERROR_RECOGNIZER_BUSY:
                        message = "인식 시도 중";
                        break;

                    case SpeechRecognizer.ERROR_SERVER:
                        message = "서버가 이상함";
                        break;

                    case SpeechRecognizer.ERROR_SPEECH_TIMEOUT:
                        message = "말하는 시간 초과";
                        break;

                    default:
                        message = "알 수 없는 에러";
                        break;
                }

                Toast.makeText(getApplicationContext(), message, Toast.LENGTH_SHORT).show();
            }

            @Override
            public void onResults(Bundle results) {
                ArrayList<String> matches = results.getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION);

                for (int i=0; i<matches.size(); i++) {
                    tvResult.setText(matches.get(i));
                }
            }

            @Override
            public void onPartialResults(Bundle partialResults) {

            }

            @Override
            public void onEvent(int eventType, Bundle params) {

            }
        };
    }

}

실행 후 버튼 클릭 후 말하면 텍스트 뷰에 반영됨.

성능은 좋지 않음.