Android语音识别的具体实现实例

最新推荐文章于 2024-04-03 07:50:36 发布

JerryHe

最新推荐文章于 2024-04-03 07:50:36 发布

阅读量4k

点赞数 1

分类专栏： Ubuntu 语音技术 Android

Android 同时被 3 个专栏收录

134 篇文章 3 订阅

订阅专栏

Ubuntu

44 篇文章 1 订阅

订阅专栏

语音技术

3 篇文章 0 订阅

订阅专栏

Android语音识别的具体实现实例

-------------------------------------------------------------------------------------------

Google语音识别

http://www.apkbus.com/forum.php?mod=viewthread&tid=3473

http://blog.csdn.net/wangkuifeng0118/article/details/7251813

本质上这三个实例的代码均来自Android源码

-------------------------------------------------------------------------------------------

Android语音识别方法一：使用intent调用语音识别程序

1.说明

以下例程功能为：在应用程序中使用intent来调出语言识别界面，录音并识别后将识别的字串返回给应用程序。注意：使用前需要安装语音识别程序如语音搜索。

2.本例参考自android例程：

development/samples/ApiDemos/src/com/example/android/apis/app/VoiceRecognition.java

3.核心代码及说明

package com.android.mystt1;  
   
import android.app.Activity;  
import android.content.Intent;  
import android.content.pm.PackageManager;  
import android.content.pm.ResolveInfo;  
import android.os.Bundle;  
import android.speech.RecognizerIntent;  
import android.view.View;  
import android.view.View.OnClickListener;  
import android.widget.ArrayAdapter;  
import android.widget.Button;  
import android.widget.ListView;  
   
import java.util.ArrayList;  
import java.util.List;  
   
public class MyStt1Activity extends Activity implements OnClickListener {  
       private static final int VOICE_RECOGNITION_REQUEST_CODE = 1234;  
       private ListView mList;          // 显示识别后字串的list控件  
   
       @Override  
       public void onCreate(Bundle savedInstanceState) {  
                super.onCreate(savedInstanceState);  
                setContentView(R.layout.main);  
                Button speakButton = (Button) findViewById(R.id.btn_speak); // 识别按钮  
                 mList = (ListView) findViewById(R.id.list);  
                PackageManager pm = getPackageManager();  
                List activities = pm.queryIntentActivities(  
                          new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH), 0); //本地识别程序  
//                       new Intent(RecognizerIntent.ACTION_WEB_SEARCH), 0); // 网络识别程序  
                if (activities.size() != 0) {  
                         speakButton.setOnClickListener(this);  
                } else {                 // 若检测不到语音识别程序在本机安装，测将扭铵置灰  
                         speakButton.setEnabled(false);  
                         speakButton.setText("Recognizer not present");  
                }  
       }  
   
       public void onClick(View v) {  
                if (v.getId() == R.id.btn_speak) {  
                         startMysttActivityActivity();  
                }  
       }  
   
       private void startMysttActivityActivity() {          // 开始识别  
                Intent intent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);  
                intent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL,  
                                   RecognizerIntent.LANGUAGE_MODEL_FREE_FORM);  
                intent.putExtra(RecognizerIntent.EXTRA_PROMPT, "Speech recognition demo");  
                startActivityForResult(intent, VOICE_RECOGNITION_REQUEST_CODE);  
                // 调出识别界面  
    }  
   
       @Override  
    protected void onActivityResult(int requestCode, int resultCode, Intent data) {  
                if (requestCode == VOICE_RECOGNITION_REQUEST_CODE && resultCode == RESULT_OK) {  
                         // Fill the list view with the strings the recognizer thought it could have heard  
                         ArrayList matches = data.getStringArrayListExtra(  
                                            RecognizerIntent.EXTRA_RESULTS);  
                         mList.setAdapter(new ArrayAdapter(this, android.R.layout.simple_list_item_1,  
                                            matches));  
                }  
                // 语音识别后的回调，将识别的字串在list中显示  
                super.onActivityResult(requestCode, resultCode, data);  
       }  
}

Android语音识别方法二：应用程序自己调用语音识别库

1.说明

以下例程功能为：应用程序自身调用语言识别函数，程序以循环方式等待录音并识别后的字串。

2.本例参考自android代码：

frameworks/base/core/java/android/speech/srec/Recognizer.java中注释部分

3.核心代码及说明

package com.android.mystt2;  
   
import android.app.Activity;  
import android.content.Intent;  
import android.os.Bundle;  
import android.widget.Button;  
import android.widget.TextView;  
import android.view.View;  
import android.view.View.OnClickListener;  
   
import android.speech.srec.Recognizer;  
import android.speech.srec.MicrophoneInputStream;  
import java.io.InputStream;  
import java.io.IOException;  
import android.util.Log;  
   
public class MyStt2Activity extends Activity implements OnClickListener {  
       private TextView mText;  
       private static final String TAG = "MyStt3Activity";  
   
       @Override  
       public void onCreate(Bundle savedInstanceState) {  
                super.onCreate(savedInstanceState);  
                setContentView(R.layout.main);  
                Button speakButton = (Button) findViewById(R.id.btn_speak);     // 识别扭按  
                mText = (TextView) findViewById(R.id.text);     // 显示识别后的字串  
                speakButton.setOnClickListener(this);  
       }  
   
       public void onClick(View v) {  
                if (v.getId() == R.id.btn_speak) {  
                         test();  
                }  
       }  
   
       void test() {  
            try {  
                InputStream audio = new MicrophoneInputStream(11025, 11025 * 5); //设置输入参数  
                String cdir = Recognizer.getConfigDir(null); // 获取语音识别配置目录
                Recognizer recognizer = new Recognizer(cdir + "/baseline11k.par");  
                Recognizer.Grammar grammar = recognizer.new Grammar(cdir  
                                            + "/grammars/VoiceDialer.g2g");  
                grammar.setupRecognizer();  
                grammar.resetAllSlots();  
                grammar.compile();  
                recognizer.start();        // 开始识别  
                while (true) {       // 循环等待识别结果  
                     switch (recognizer.advance()) {  
                        case Recognizer.EVENT_INCOMPLETE:  
                        case Recognizer.EVENT_STARTED:  
                        case Recognizer.EVENT_START_OF_VOICING:  
                        case Recognizer.EVENT_END_OF_VOICING:  
                             continue;    // 未完成，继续等待识别结果  
                        case Recognizer.EVENT_RECOGNITION_RESULT:  
                            for (int i = 0; i < recognizer.getResultCount(); i++) {                                 String result = recognizer.getResult(i,  
                                                  Recognizer.KEY_LITERAL);  
                                 Log.d(TAG, "result " + result);  
                                 mText.setText(result);  
                             }        // 识别到字串，显示并退出循环  
                             break;  
                         case Recognizer.EVENT_NEED_MORE_AUDIO:  
                              recognizer.putAudio(audio)   // 需要更多音频数据;  
                              continue;  
                          default:  
                              break;  
                          }  
                            break;  
                         }  
                         recognizer.stop();  
                         recognizer.destroy();  
                         audio.close();      // 回收资源  
                } catch (IOException e) {  
                         Log.d(TAG, "error", e);  
                         mText.setText("error " + e);  
                }  
       }  
}

Android语音识别方法三：使用Service调用语音识别程序

1.说明

以下例程功能为：在应用程序中使用通于访问service调用语言识别功能，录音并识别后将识别的字串通过Listener返回给应用程序。注意：使用前需要安装语音识别服务，如编译安装源码中的development/samples/VoiceRecogitionService。

2.本例参考自android源码

a)后台服务

参见development/samples/VoiceRecognitionService/*

此处实现了一个模拟的后台服务，它并未实现真的语音识别，而只是一个框架以示例，编译并安装它，即可在设置的语音输入与输出中看到它，它包含了一个设置界面，当连接这个Service时，如果设置了Letters，则直接返回abc，如果设置了Numbers，则直接返回123

你可以自己实现，用于连接android源码自带的识别引擎srec.

b)前台程序

参见frameworks/base/core/java/android/speech/Recognition*

它与后台Service交互，此段代码实现在应用程序界面中

3.核心代码及说明

package com.android.mystt3;  
   
import android.app.Activity;  
import android.content.Intent;  
import android.os.Bundle;  
import android.view.View;  
import android.view.View.OnClickListener;  
import android.speech.RecognitionListener;  
import android.speech.RecognizerIntent;  
import android.speech.SpeechRecognizer;  
import android.widget.Button;  
import android.widget.TextView;  
import java.util.ArrayList;  
import android.util.Log;  
   
public class MyStt3Activity extends Activity implements OnClickListener {  
       private TextView mText;  
       private SpeechRecognizer sr;  
       private static final String TAG = "MyStt3Activity";  
   
       @Override  
       public void onCreate(Bundle savedInstanceState) {  
                super.onCreate(savedInstanceState);  
                setContentView(R.layout.main);  
                Button speakButton = (Button) findViewById(R.id.btn_speak);     // 识别按钮  
                mText = (TextView) findViewById(R.id.text);      // 显示识别字串  
                speakButton.setOnClickListener(this);  
                sr = SpeechRecognizer.createSpeechRecognizer(this);        // 初始化识别工具，得到句柄  
                sr.setRecognitionListener(new listener());         // 注册回调类及函数  
       }  
   
       class listener implements RecognitionListener            // 回调类的实现  
       {  
                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)  
                {  
                         Log.d(TAG,  "error " +  error);  
                         mText.setText("error " + error);  
                }  
                public void onResults(Bundle results)     // 返回识别到的数据  
                {  
                         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);  
                         }  
                         mText.setText(str);        // 显示被识别的数据  
                }  
                public void onPartialResults(Bundle partialResults)  
                {  
                         Log.d(TAG, "onPartialResults");  
                }  
                public void onEvent(int eventType, Bundle params)  
                {  
                         Log.d(TAG, "onEvent " + eventType);  
                }  
       }  
   
       public void onClick(View v) {  
                if (v.getId() == R.id.btn_speak) {  
                         sr.startListening(new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH));  
                }  
       }  
}