android 文本转成Uri android文字转语音

转载

mob64ca140a1f7c 2023-09-12 20:26:03

文章标签 android 文本转成Uri 语音识别人工智能 android java 文章分类 Android 移动开发

一、系统自带的语音引擎

语音播报的本质是将书面文字转换成自然语言的音频流，这个转换操作被称作语音合成，又称TTS（从文本到语音）在转换过程中，为了避免机械合成的呆板和停顿感，语音合成技术还得对语音流进行平滑处理，以确保输出得语音音律流畅自然。

不管是Android原生的西文引擎还是手机厂商集成的中文引擎，都支持通过系统提供的API处理语音，其中的语音合成工具是TextToSpeech 常用方法如下

构造方法：第二个输入参数为语音监听器
setLanguage：设置引擎语言
setSpeechRate 设置语速
setPitch 设置音调
synthesizeToFile 把指定文本的朗读语言输出到文件

实战效果如下

android 文本转成Uri android文字转语音_语音识别

代码如下

Java类

package com.example.voice;

import android.content.Intent;
import android.os.Bundle;
import android.speech.tts.TextToSpeech;
import android.view.View;
import android.widget.AdapterView;
import android.widget.ArrayAdapter;
import android.widget.ListView;
import android.widget.Spinner;

import androidx.appcompat.app.AppCompatActivity;

import com.example.voice.adapter.LanguageListAdapter;
import com.example.voice.bean.Language;

import java.util.ArrayList;
import java.util.List;
import java.util.Locale;

public class SpeechEngineActivity extends AppCompatActivity {
    private final static String TAG = "SpeechEngineActivity";
    private TextToSpeech mSpeech; // 声明一个文字转语音对象

    @Override
    protected void onCreate(Bundle savedInstanceState) {
        super.onCreate(savedInstanceState);
        setContentView(R.layout.activity_speech_engine);
        findViewById(R.id.btn_jump_setting).setOnClickListener(v -> {
            Intent intent = new Intent();
            intent.setAction("com.android.settings.TTS_SETTINGS");
            startActivity(intent);
        });
        // 创建一个文字转语音对象，初始化结果在监听器TTSListener中返回
        mSpeech = new TextToSpeech(this, new TTSListener());
    }

    private List<TextToSpeech.EngineInfo> mEngineList; // 语音引擎列表
    // 定义一个文字转语音的初始化监听器
    private class TTSListener implements TextToSpeech.OnInitListener {
        // 在初始化完成时触发
        @Override
        public void onInit(int status) {
            if (status == TextToSpeech.SUCCESS) { // 初始化成功
                if (mEngineList == null) { // 首次初始化
                    // 获取系统支持的所有语音引擎
                    mEngineList = mSpeech.getEngines();
                    initEngineSpinner(); // 初始化语音引擎下拉框
                }
                initLanguageList(); // 初始化语言列表
            }
        }
    }

    // 初始化语音引擎下拉框
    private void initEngineSpinner() {
        String[] engineArray = new String[mEngineList.size()];
        for(int i=0; i<mEngineList.size(); i++) {
            engineArray[i] = mEngineList.get(i).label;
        }
        ArrayAdapter<String> engineAdapter = new ArrayAdapter<>(this,
                R.layout.item_select, engineArray);
        Spinner sp_engine = findViewById(R.id.sp_engine);
        sp_engine.setPrompt("请选择语音引擎");
        sp_engine.setAdapter(engineAdapter);
        sp_engine.setOnItemSelectedListener(new EngineSelectedListener());
        sp_engine.setSelection(0);
    }

    private class EngineSelectedListener implements AdapterView.OnItemSelectedListener {
        public void onItemSelected(AdapterView<?> arg0, View arg1, int arg2, long arg3) {
            //recycleSpeech(); // 回收文字转语音对象
            // 创建指定语音引擎的文字转语音对象
            mSpeech = new TextToSpeech(SpeechEngineActivity.this, new TTSListener(),
                    mEngineList.get(arg2).name);
        }

        public void onNothingSelected(AdapterView<?> arg0) {}
    }

    private String[] mLanguageArray = {"中文普通话", "英语", "法语", "德语", "意大利语",  };
    private Locale[] mLocaleArray = { Locale.CHINA, Locale.ENGLISH, Locale.FRENCH, Locale.GERMAN, Locale.ITALIAN };

    // 初始化语言列表
    private void initLanguageList() {
        List<Language> languageList = new ArrayList<>();
        // 下面遍历语言数组，从中挑选出当前引擎所支持的语言列表
        for (int i=0; i<mLanguageArray.length; i++) {
            String desc = "正常使用";
            // 设置朗读语言
            int result = mSpeech.setLanguage(mLocaleArray[i]);
            if (result == TextToSpeech.LANG_MISSING_DATA) {
                desc = "缺少数据";
            } else if (result == TextToSpeech.LANG_NOT_SUPPORTED) {
                desc = "暂不支持";
            }
            languageList.add(new Language(mLanguageArray[i], desc));
        }
        // 下面把该引擎对各语言的支持情况展示到列表视图上
        ListView lv_language = findViewById(R.id.lv_language);
        LanguageListAdapter adapter = new LanguageListAdapter(this, languageList);
        lv_language.setAdapter(adapter);
    }

}

二、文字转语音

既然明确了一个引擎能够支持哪些语言，接下来就可以大胆设置朗读的语言了，并且设置好语言后，还得提供对应的文字才可以，下面是一个语音播报页面的实例

中文普通话播报

android 文本转成Uri android文字转语音_android_02

英文版播报

android 文本转成Uri android文字转语音_java_03

可以在下拉框中选择自己想要朗读的语言

android 文本转成Uri android文字转语音_android 文本转成Uri_04

代码如下

Java类

package com.example.voice;

import android.os.Bundle;
import android.speech.tts.TextToSpeech;
import android.util.Log;
import android.view.View;
import android.widget.AdapterView;
import android.widget.ArrayAdapter;
import android.widget.EditText;
import android.widget.Spinner;
import android.widget.Toast;

import androidx.appcompat.app.AppCompatActivity;

import com.example.voice.bean.Language;

import java.util.ArrayList;
import java.util.List;
import java.util.Locale;

public class SpeechComposeActivity extends AppCompatActivity {
    private final static String TAG = "SpeechComposeActivity";
    private TextToSpeech mSpeech; // 声明一个文字转语音对象
    private EditText et_tts; // 声明一个编辑框对象
    private List<TextToSpeech.EngineInfo> mEngineList; // 语音引擎列表

    @Override
    protected void onCreate(Bundle savedInstanceState) {
        super.onCreate(savedInstanceState);
        setContentView(R.layout.activity_speech_compose);
        et_tts = findViewById(R.id.et_tts);
        findViewById(R.id.btn_read).setOnClickListener(v -> {
            String content = et_tts.getText().toString();
            // 开始朗读指定文本
            int result = mSpeech.speak(content, TextToSpeech.QUEUE_FLUSH, null, null);
            String desc = String.format("朗读%s", result==TextToSpeech.SUCCESS?"成功":"失败");
            Toast.makeText(this, desc, Toast.LENGTH_SHORT).show();
        });
        // 创建一个文字转语音对象，初始化结果在监听器的onInit方法中返回
        mSpeech = new TextToSpeech(this, mListener);
    }

    // 创建一个文字转语音的初始化监听器实例
    private TextToSpeech.OnInitListener mListener = status -> {
        if (status == TextToSpeech.SUCCESS) { // 初始化成功
            if (mEngineList == null) { // 首次初始化
                mEngineList = mSpeech.getEngines(); // 获取系统支持的所有语音引擎
                initEngineSpinner(); // 初始化语音引擎下拉框
            }
            initLanguageSpinner(); // 初始化语言下拉框
        }
    };

    // 初始化语音引擎下拉框
    private void initEngineSpinner() {
        String[] engineArray = new String[mEngineList.size()];
        for(int i=0; i<mEngineList.size(); i++) {
            engineArray[i] = mEngineList.get(i).label;
        }
        ArrayAdapter<String> engineAdapter = new ArrayAdapter<>(this,
                R.layout.item_select, engineArray);
        Spinner sp_engine = findViewById(R.id.sp_engine);
        sp_engine.setPrompt("请选择语音引擎");
        sp_engine.setAdapter(engineAdapter);
        sp_engine.setOnItemSelectedListener(new EngineSelectedListener());
        sp_engine.setSelection(0);
    }

    private class EngineSelectedListener implements AdapterView.OnItemSelectedListener {
        public void onItemSelected(AdapterView<?> arg0, View arg1, int arg2, long arg3) {
            recycleSpeech(); // 回收文字转语音对象
            // 创建指定语音引擎的文字转语音对象
            mSpeech = new TextToSpeech(SpeechComposeActivity.this, mListener,
                    mEngineList.get(arg2).name);
        }

        public void onNothingSelected(AdapterView<?> arg0) {}
    }

    // 回收文字转语音对象
    private void recycleSpeech() {
        if (mSpeech != null) {
            mSpeech.stop(); // 停止文字转语音
            mSpeech.shutdown(); // 关闭文字转语音
            mSpeech = null;
        }
    }

    @Override
    protected void onDestroy() {
        super.onDestroy();
        recycleSpeech(); // 回收文字转语音对象
    }

    private String[] mLanguageArray = {"中文普通话", "英语", "法语", "德语", "意大利语"};
    private Locale[] mLocaleArray = { Locale.CHINA, Locale.ENGLISH, Locale.FRENCH, Locale.GERMAN, Locale.ITALIAN };
    private String[] mValidLanguageArray; // 当前引擎支持的语言名称数组
    private Locale[] mValidLocaleArray; // 当前引擎支持的语言类型数组
    private String mTextCN = "离离原上草，一岁一枯荣。野火烧不尽，春风吹又生。";
    private String mTextEN = "Hello World. Nice to meet you. This is a TTS demo.";

    // 初始化语言下拉框
    private void initLanguageSpinner() {
        List<Language> languageList = new ArrayList<>();
        // 下面遍历语言数组，从中挑选出当前引擎所支持的语言列表
        for (int i=0; i<mLanguageArray.length; i++) {
            // 设置朗读语言。通过检查方法的返回值，判断引擎是否支持该语言
            int result = mSpeech.setLanguage(mLocaleArray[i]);
            Log.d(TAG, "language="+mLanguageArray[i]+",result="+result);
            if (result != TextToSpeech.LANG_MISSING_DATA
                    && result != TextToSpeech.LANG_NOT_SUPPORTED) { // 语言可用
                languageList.add(new Language(mLanguageArray[i], mLocaleArray[i]));
            }
        }
        mValidLanguageArray = new String[languageList.size()];
        mValidLocaleArray = new Locale[languageList.size()];
        for(int i=0; i<languageList.size(); i++) {
            mValidLanguageArray[i] = languageList.get(i).name;
            mValidLocaleArray[i] = languageList.get(i).locale;
        }
        // 下面初始化语言下拉框
        ArrayAdapter<String> languageAdapter = new ArrayAdapter<>(this,
                R.layout.item_select, mValidLanguageArray);
        Spinner sp_language = findViewById(R.id.sp_language);
        sp_language.setPrompt("请选择朗读语言");
        sp_language.setAdapter(languageAdapter);
        sp_language.setOnItemSelectedListener(new LanguageSelectedListener());
        sp_language.setSelection(0);
    }

    private class LanguageSelectedListener implements AdapterView.OnItemSelectedListener {
        public void onItemSelected(AdapterView<?> arg0, View arg1, int arg2, long arg3) {
            if (mValidLocaleArray[arg2]==Locale.CHINA) { // 汉语
                et_tts.setText(mTextCN);
            } else { // 其他语言
                et_tts.setText(mTextEN);
            }
            mSpeech.setLanguage(mValidLocaleArray[arg2]); // 设置选中的朗读语言
        }

        public void onNothingSelected(AdapterView<?> arg0) {}
    }

}

三、原生的语音识别

Android提供了语音识别器SpeechRecognizer 该工具常用方法如下

isRecognitionAvailable 检查系统是否支持原生的语音识别
createSpeechRecognizer 创建原生的语音识别器对象
setRecognitionListener 设置语音识别监听器
startListening 开始语音识别
stopListening 停止语音识别
cancel 取消语音识别
destroy 销毁语音识别器

识别结果监听器提供了许多回调方法，其中onResults方法可获得识别后的文本信息，然而每个引擎对文本结果的包装结构不尽相同，比如百度语音返回JSON格式的字符串，而讯飞语音返回字符串列表，为此要分别尝试几种格式的文本识别效果如下

android 文本转成Uri android文字转语音_android 文本转成Uri_05

结果如下点击开始识别后对着麦克风说话停止识别后则会自动输出识别内容

此处连接真机测试更佳模拟机可能没有麦克风~~~

android 文本转成Uri android文字转语音_android 文本转成Uri_06

代码如下

java类

package com.example.voice;

import androidx.appcompat.app.AppCompatActivity;

import android.annotation.SuppressLint;
import android.content.ComponentName;
import android.content.Intent;
import android.graphics.Color;
import android.os.Bundle;
import android.provider.Settings;
import android.speech.RecognitionListener;
import android.speech.RecognizerIntent;
import android.speech.SpeechRecognizer;
import android.util.Log;
import android.widget.Button;
import android.widget.TextView;

import org.json.JSONArray;
import org.json.JSONObject;

import java.util.List;
import java.util.Locale;

@SuppressLint("SetTextI18n")
public class SpeechRecognizeActivity extends AppCompatActivity implements RecognitionListener {
    private final static String TAG = "SpeechRecognizeActivity";
    private TextView tv_result; // 声明一个文本视图对象
    private Button btn_recognize; // 声明一个按钮对象
    private SpeechRecognizer mRecognizer; // 声明一个语音识别对象
    private boolean isRecognizing = false; // 是否正在识别

    @Override
    protected void onCreate(Bundle savedInstanceState) {
        super.onCreate(savedInstanceState);
        setContentView(R.layout.activity_speech_recognize);
        tv_result = findViewById(R.id.tv_result);
        btn_recognize = findViewById(R.id.btn_recognize);
        // 检查系统是否支持原生的语音识别
        boolean enable = SpeechRecognizer.isRecognitionAvailable(this);
        if (enable) {
            initRecognize(); // 初始化语音识别
        } else {
            tv_result.setText("原生的语音识别服务不可用");
            btn_recognize.setEnabled(false);
            btn_recognize.setTextColor(Color.GRAY);
        }
    }

    // 初始化语音识别
    private void initRecognize() {
        String serviceComponent = Settings.Secure.getString(
                getContentResolver(), "voice_recognition_service");
        // 获得系统内置的语音识别服务
        ComponentName component = ComponentName.unflattenFromString(serviceComponent);
        Log.d(TAG, "getPackageName="+component.getPackageName()+",getClassName="+component.getClassName());
        tv_result.setText("原生的语音识别服务采用"+component.getPackageName()
                +"里的服务"+component.getClassName());
        // 创建原生的语音识别器对象
        mRecognizer = SpeechRecognizer.createSpeechRecognizer(this);
        mRecognizer.setRecognitionListener(this); // 设置语音识别监听器
        btn_recognize.setOnClickListener(v -> {
            if (!isRecognizing) { // 未在识别
                Intent intent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
                intent.putExtra(RecognizerIntent.EXTRA_PARTIAL_RESULTS, true);
                intent.putExtra(RecognizerIntent.EXTRA_LANGUAGE, Locale.CHINA);
                intent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL,
                        RecognizerIntent.LANGUAGE_MODEL_FREE_FORM);
                intent.putExtra(RecognizerIntent.EXTRA_MAX_RESULTS, 5);
                mRecognizer.startListening(intent); // 开始语音识别
            } else { // 正在识别
                mRecognizer.stopListening(); // 停止语音识别
                //mRecognizer.cancel(); // 取消语音识别
            }
            isRecognizing = !isRecognizing;
            btn_recognize.setText(isRecognizing?"停止识别":"开始识别");
        });
    }

    @Override
    public void onReadyForSpeech(Bundle params) {}

    @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) {
        Log.d(TAG, "Recognize error:"+error);
    }

    @Override
    public void onResults(Bundle results) {
        Log.d(TAG, "onResults Start");
        String desc = "";
        String key = SpeechRecognizer.RESULTS_RECOGNITION;
        try { // 百度语音分支
            String result = results.getString(key);
            Log.d(TAG, "result="+result);
            JSONObject object = new JSONObject(result);
            String recognizeResult = object.getString("recognizeResult");
            JSONArray recognizeArray = new JSONArray(recognizeResult);
            for (int i=0; i<recognizeArray.length(); i++) {
                JSONObject item = (JSONObject) recognizeArray.get(i);
                String se_query = item.getString("se_query");
                desc = desc + "\n" + se_query;
                Log.d(TAG, "desc="+desc);
            }
        } catch (Exception e) { // 讯飞语音分支
            e.printStackTrace();
            List<String> resultList = results.getStringArrayList(key);
            for (String str : resultList) {
                desc = desc + "\n" + str;
                Log.d(TAG, "desc="+desc);
            }
        }
        tv_result.setText("识别到的文字为："+desc);
        Log.d(TAG, "onResults End");
    }

    @Override
    public void onPartialResults(Bundle partialResults) {
        Log.d(TAG, "onPartialResults");
    }

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

    @Override
    protected void onDestroy() {
        super.onDestroy();
        if (mRecognizer != null) {
            mRecognizer.destroy(); // 销毁语音识别器
        }
    }

}

本文章为转载内容，我们尊重原作者对文章享有的著作权。如有内容错误或侵权问题，欢迎原作者联系我们进行内容更正或删除文章。