Android使用百度语音识别

辛苦堆砌，转载请注明出处，谢谢！

考虑很多读者反馈的问题，对文章进行了修正，由于百度语音有些变化，有一些配置上需要变化。文章变动主要体现在几个方面：

1.配置方式改变；

2.使用Kotlin实现;

3.附github代码地址。

按照百度官网的配置说明，将百度语音相关的so放置在app\src\main\jniLibs目录下(armeabi等目录一起拷贝过去)，这个目录是默认的Android放置NDK的so的目录，然后将jar文件，放置在app\libs

Manifest文件中添加权限

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

然后还要在Manifest中添加

 <meta-data android:name="com.baidu.speech.APP_ID" android:value="Your APP_ID" />
 <meta-data android:name="com.baidu.speech.API_KEY" android:value="Your API_KEY" />
 <meta-data android:name="com.baidu.speech.SECRET_KEY" android:value="Your SECRET_KEY" />

 <service android:name="com.baidu.speech.VoiceRecognitionService" android:exported="false" />

其中的APP ID，API_KEY和SECRET_KEY替换为你申请的内容。

我们封装了一个工具类，用来使用语音识别

 package com.example.yjp.baiduspeechdemo

 import android.content.ComponentName
 import android.content.Context
 import android.content.Intent
 import android.os.Bundle
 import android.speech.RecognitionListener
 import android.speech.SpeechRecognizer
 import android.widget.Toast

 import com.baidu.speech.VoiceRecognitionService

 class SpeechRecognizerTool(private val mContext: Context) : RecognitionListener {

     private var mSpeechRecognizer: SpeechRecognizer? = null

     private var mResultsCallback: ResultsCallback? = null

     interface ResultsCallback {
         fun onResults(result: String)
     }

     @Synchronized
     fun createTool() {
         if (null == mSpeechRecognizer) {

             // 创建识别器
             mSpeechRecognizer = SpeechRecognizer.createSpeechRecognizer(mContext,
                     ComponentName(mContext, VoiceRecognitionService::class.java))

             // 注册监听器
             mSpeechRecognizer!!.setRecognitionListener(this)
         }
     }

     @Synchronized
     fun destroyTool() {
         mSpeechRecognizer!!.stopListening()
         mSpeechRecognizer!!.destroy()
         mSpeechRecognizer = null
     }

     // 开始识别
     fun startASR(callback: ResultsCallback) {
         mResultsCallback = callback

         val intent = Intent()
         bindParams(intent)
         mSpeechRecognizer!!.startListening(intent)
     }

     //停止识别
     fun stopASR() {
         mSpeechRecognizer!!.stopListening()
     }

     private fun bindParams(intent: Intent) {
         // 设置识别参数
     }

     override fun onReadyForSpeech(params: Bundle) {
         // 准备就绪
         Toast.makeText(mContext, "请开始说话", Toast.LENGTH_SHORT).show()
     }

     override fun onBeginningOfSpeech() {
         // 开始说话处理
     }

     override fun onRmsChanged(rmsdB: Float) {
         // 音量变化处理
     }

     override fun onBufferReceived(buffer: ByteArray) {
         // 录音数据传出处理
     }

     override fun onEndOfSpeech() {
         // 说话结束处理
     }

     override fun onError(error: Int) {}

     override fun onResults(results: Bundle) {

         // 最终结果处理
         if (mResultsCallback != null) {
             val text = results.get(SpeechRecognizer.RESULTS_RECOGNITION)!!
                     .toString().replace("]", "").replace("[", "")
             mResultsCallback!!.onResults(text)
         }
     }

     override fun onPartialResults(partialResults: Bundle) {
         // 临时结果处理
     }

     override fun onEvent(eventType: Int, params: Bundle) {}
 }

MainActivity的类实现为：

 package com.example.yjp.baiduspeechdemo

 import android.Manifest
 import android.content.pm.PackageManager
 import android.os.Bundle
 import android.support.v4.app.ActivityCompat
 import android.support.v4.content.ContextCompat
 import android.support.v7.app.AppCompatActivity
 import android.view.MotionEvent
 import kotlinx.android.synthetic.main.activity_main.*


 class MainActivity : AppCompatActivity(), SpeechRecognizerTool.ResultsCallback {

     private val mSpeechRecognizerTool = SpeechRecognizerTool(this)

     override fun onCreate(savedInstanceState: Bundle?) {
         super.onCreate(savedInstanceState)
         setContentView(R.layout.activity_main)

         initPermission()

         startSpeechButton.setOnTouchListener {
             view, event ->
             val action = event.action
             when (action) {
                 MotionEvent.ACTION_DOWN -> {
                     mSpeechRecognizerTool.startASR(this@MainActivity)
                 }
                 MotionEvent.ACTION_UP -> {
                     mSpeechRecognizerTool.stopASR()
                 }
                 else -> return@setOnTouchListener false
             }

             return@setOnTouchListener true
         }
     }

     override fun onStart() {
         super.onStart()
         mSpeechRecognizerTool.createTool()
     }

     override fun onStop() {
         super.onStop()
         mSpeechRecognizerTool.destroyTool()
     }

     override fun onResults(result: String) {
         [email protected] { speechTextView!!.text = result }
     }

     private fun initPermission() {
         val permissions = arrayOf<String>(Manifest.permission.RECORD_AUDIO,
                 Manifest.permission.ACCESS_NETWORK_STATE,
                 Manifest.permission.INTERNET,
                 Manifest.permission.READ_PHONE_STATE,
                 Manifest.permission.WRITE_EXTERNAL_STORAGE)

         val toApplyList = ArrayList<String>()

         for (perm in permissions) {
             if (PackageManager.PERMISSION_GRANTED != ContextCompat.checkSelfPermission(this, perm)) {
                 toApplyList.add(perm)
                 //进入到这里代表没有权限.

             }
         }
         val tmpList = arrayOfNulls<String>(toApplyList.size)
         if (!toApplyList.isEmpty()) {
             ActivityCompat.requestPermissions(this, toApplyList.toArray(tmpList), 123)
         }
     }
 }

可以运行看一下效果，感觉识别率还是不错的。代码在这里。