實時語音轉文字app簡易demo（這裏使用了阿里的接口，能夠替換成科大訊飛）
這裏只是功能實現（我的非android開發），可能有不少更好的實現方式，該功能的開發是以前看到過阿里的實時語音轉文字的接口，當時就想把這個功能作到手機上，本身又是java開發，就百度了點基礎的android知識作了個簡單的實現。java
主方法（手機端），主要任務採集聲音，流形式發送到後臺android
package com.hht.myapplication;
import android.Manifest;
import android.text.ClipboardManager;
import android.content.Context;
import android.content.pm.PackageManager;
import android.media.AudioFormat;
import android.media.AudioRecord;
import android.media.MediaRecorder;
import android.os.Bundle;
import android.os.Handler;
import android.support.v4.app.ActivityCompat;
import android.support.v4.content.ContextCompat;
import android.support.v7.app.AppCompatActivity;
import android.text.method.ScrollingMovementMethod;
import android.view.View;
import android.widget.TextView;
import android.widget.Toast;
import java.io.DataInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.net.Socket;
/**
* 語音小助手
* hht
*/
public class MainActivity extends AppCompatActivity {
//接收轉換的文字流
DataInputStream dis;
//音頻流上傳通道
OutputStream ous;
String serverIp = "101.201.XXX.XXX";
int serverPort = 5555;
private TextView realText;
private TextView finalText;
//音頻相關
AudioRecord audioRecord=null;
int bufferSize=0;//最小緩衝區大小
int sampleRateInHz = 16000;//採樣率
int channelConfig = AudioFormat.CHANNEL_IN_DEFAULT; //單聲道
int audioFormat = AudioFormat.ENCODING_PCM_16BIT; //量化位數
private boolean isRecording = true;
private Handler handler=null;
private String content ;
@Override
protected void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
setContentView(R.layout.activity_main);
realText = (TextView) findViewById(R.id.textView2);
finalText = (TextView) findViewById(R.id.textView);
finalText.setMovementMethod(ScrollingMovementMethod.getInstance()) ;
handler = new Handler();
if (ContextCompat.checkSelfPermission(this, Manifest.permission.CALL_PHONE) != PackageManager.PERMISSION_GRANTED) {
ActivityCompat.requestPermissions(this, new String[]{Manifest.permission.RECORD_AUDIO},1);
} else {
init();
}
}
public void onClickCopy(View v) {
// 從API11開始android推薦使用android.content.ClipboardManager
// 爲了兼容低版本咱們這裏使用舊版的android.text.ClipboardManager，雖然提示deprecated，但不影響使用。
ClipboardManager cm = (ClipboardManager) getSystemService(Context.CLIPBOARD_SERVICE);
// 將文本內容放到系統剪貼板裏。
cm.setText(finalText.getText());
Toast.makeText(this, "複製成功，能夠發給朋友們了。", Toast.LENGTH_LONG).show();
}
public void init(){
System.out.println("初始化錄音");
bufferSize = AudioRecord.getMinBufferSize(sampleRateInHz,channelConfig, audioFormat)+1000;//計算最小緩衝區
try{
audioRecord = new AudioRecord(MediaRecorder.AudioSource.MIC,sampleRateInHz,channelConfig, audioFormat, bufferSize);//建立AudioRecorder對象
Runnable startRunnable = new Runnable(){
@Override
public void run() {
connect();
new sendDataThread().start();
new getDataThread().start();
}
};
new Thread(startRunnable).start();
}catch (Exception e){
e.printStackTrace();
}
System.out.println("初始化錄音成功");
}
public void connect(){
try{
Socket socket = new Socket(serverIp,serverPort);
InputStream is=socket.getInputStream();
ous = socket.getOutputStream();
dis=new DataInputStream(is);
}catch(IOException e){
e.printStackTrace();
}
}
//發送數據
class sendDataThread extends Thread {
public void run() {
byte[] buffer = new byte[bufferSize];
audioRecord.startRecording();//開始錄音
int r = 0;
try {
while (isRecording&&audioRecord.read(buffer,0,bufferSize)>0) {
ous.write(buffer);
ous.flush();
}
audioRecord.stop();//中止錄音
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
//接收數據
class getDataThread extends Thread {
public void run() {
while (true) {
String msg;
try {
msg = dis.readUTF();
if (!"status".equals(msg)&&!"".equals(msg)) {//status 爲心跳檢測
content=msg;
handler.post(runnableUi);
}
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
}
}
// 構建Runnable對象，在runnable中更新界面
Runnable runnableUi=new Runnable(){
@Override
public void run() {
//更新界面
realText.setText(content);
finalText.append(content);
//跳轉到底部
int offset=finalText.getLineCount()*finalText.getLineHeight();
if(finalText.getLineCount()>15 && offset>finalText.getHeight()){
finalText.scrollTo(0,offset-finalText.getHeight());
}
}
};
@Override
public void onRequestPermissionsResult(int requestCode, String permissions[], int[] grantResults) {
switch (requestCode) {
case 1: {
if (grantResults.length > 0 && grantResults[0] == PackageManager.PERMISSION_GRANTED) {
// 權限被用戶贊成，能夠去放肆了。
init();
} else {
// 權限被用戶拒絕了，洗洗睡吧。
}
return;
}
}
}
}
服務器端，接收流信息上傳阿里獲取實時轉換結果，這裏應該有本身的控制策略，我這裏只作了實現，策略沒有哦web
這部分代碼是接收和處理客戶端請求json
package com.hmkx.freezingapi.rest.jkjweb;
import java.io.Closeable;
import java.io.DataOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.net.ServerSocket;
import java.net.Socket;
import java.util.ArrayList;
import java.util.List;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.hmkx.freezingapi.util.ali.RealtimeAsrDemo;
/**
* 語音轉換服務 監聽
*
* @author hht
* @since 2018-06-12
*/
public class AudioChangeServerThread extends Thread {
private static Logger log = LoggerFactory.getLogger(AudioChangeServerThread.class);
static int cCount = 0;//當前鏈接數
static int maxCount = 10;//最大鏈接數
static ServerSocket server = null;
static List<DataOutputStream>socketsOut = new ArrayList<DataOutputStream>();
static List<Socket>sockets = new ArrayList<Socket>();
public static boolean runStatus = false;//標記狀態 關閉後再也不接受鏈接
public void run(){
runStatus = true;
if(server==null){//語音轉換服務監聽
try {
server = new ServerSocket(5555);
} catch (IOException e) {
e.printStackTrace();
}
while (runStatus) {
//每接受一個鏈接，清理半關閉的鏈接
validateSocket();
if(cCount<=maxCount){
try {
Socket temp = server.accept();
sockets.add(temp);
OutputStream os=temp.getOutputStream();
DataOutputStream dos=new DataOutputStream(os);
InputStream ins = temp.getInputStream();
RealtimeAsrDemo lun = new RealtimeAsrDemo(ins,dos);
log.error("audio change start ....");
new Thread(lun).start();
cCount++;
} catch (IOException e) {
log.error("has connected io exception");
}
log.error("has connected "+cCount);
}
}
}
}
/**
* 清楚已經斷開的鏈接
* @param i
*/
public static void removeSocket(int i){
Aclose(sockets.get(i));
Aclose(socketsOut.get(i));
sockets.remove(i);
socketsOut.remove(i);
cCount--;
}
/**
* 清楚已經斷開的鏈接
* @param i
*/
public void validateSocket(){
for(int i=0;i<socketsOut.size();i++){
try {
DataOutputStream temp = socketsOut.get(i);
temp.writeUTF("status");
temp.flush();
} catch (Exception e) {
removeSocket(i);
}
}
}
/**
* 鏈接關閉方法
* @param o
*/
public static void Aclose(Object...o){
for(int i=0;i<o.length;i++){
if(o[i] instanceof Closeable){
try {
Closeable c = (Closeable)o[i];
c.close();
} catch (IOException e) {
e.printStackTrace();
}
}
if(o[i] instanceof ServerSocket){
try {
ServerSocket c = (ServerSocket)o[i];
c.close();
} catch (IOException e) {
e.printStackTrace();
}
}
if(o[i] instanceof Socket){
try {
Socket c = (Socket)o[i];
c.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
}
}
下面這部分代碼是處理流和阿里雲服務接口的交互，用到阿里的包這個自行引入，（最近科大訊飛也提供了相似的接口，貌似效果更好）能夠替換這部分邏輯就能夠api
package com.hmkx.freezingapi.util.ali;
import java.io.DataOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.PrintWriter;
import java.io.StringWriter;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.alibaba.fastjson.JSON;
import com.alibaba.idst.nls.realtime.NlsClient;
import com.alibaba.idst.nls.realtime.NlsFuture;
import com.alibaba.idst.nls.realtime.event.NlsEvent;
import com.alibaba.idst.nls.realtime.event.NlsListener;
import com.alibaba.idst.nls.realtime.protocol.NlsRequest;
import com.alibaba.idst.nls.realtime.protocol.NlsResponse;
import com.hmkx.freezingapi.rest.jkjweb.AudioChangeServerThread;
/**
* 語音實時轉文字工具類
*
* @author hht
*
*/
public class RealtimeAsrDemo implements NlsListener,Runnable{
protected NlsClient client = new NlsClient();
protected static final String asrSC = "pcm";
static Logger logger = LoggerFactory.getLogger(RealtimeAsrDemo.class);
public String appKey = "XXX";
protected String ak_id = "XXX";
protected String ak_secret = "XXX";
private InputStream fis = null;
private DataOutputStream dos = null;
public RealtimeAsrDemo(InputStream fis, DataOutputStream dos) {
this.fis = fis;
this.dos = dos;
}
public void shutDown() {
logger.error("close NLS client manually!");
client.close();
logger.error("demo done");
}
public void init() {
logger.error("init Nls client...");
client.init();
}
public void process() {
logger.error("open audio file...");
if (fis != null) {
logger.error("create NLS future");
process(fis);
logger.error("calling NLS service end");
}
}
public void process(InputStream ins) {
try {
NlsRequest req = buildRequest();
NlsFuture future = client.createNlsFuture(req, this);
logger.error("call NLS service");
byte[] b = new byte[8000];
int len = 0;
while (AudioChangeServerThread.runStatus && (len = ins.read(b)) > 0 ) {
future.sendVoice(b, 0, len);
}
logger.error("send finish signal!");
future.sendFinishSignal();
logger.error("main thread enter waiting .");
future.await(100000);
} catch (Exception e) {
StringWriter sw = new StringWriter();
e.printStackTrace(new PrintWriter(sw));
logger.error(sw.toString());
}
}
protected NlsRequest buildRequest() {
NlsRequest req = new NlsRequest();
req.setAppkey(appKey);
req.setFormat(asrSC);
req.setResponseMode("streaming");
req.setSampleRate(16000);
// 用戶根據[熱詞文檔](~~49179~~) 設置自定義熱詞。
// 經過設置VocabularyId調用熱詞。
// req.setVocabularyId("");
// 設置關鍵詞庫ID 使用時請修改成自定義的詞庫ID
// req.setKeyWordListId("c1391f1c1f1b4002936893c6d97592f3");
// the id and the id secret
req.authorize(ak_id, ak_secret);
return req;
}
@Override
public void onMessageReceived(NlsEvent e) {
NlsResponse response = e.getResponse();
response.getFinish();
if (response.result != null) {
logger.error(response.getResult().toString());
if(response.getResult().getStatus_code()==0&&!"".equals(response.getText())){
String content = response.getText();
logger.error(content);
try {
dos.writeUTF(content);
dos.flush();
} catch (IOException e1) {
// TODO Auto-generated catch block
e1.printStackTrace();
}
}
} else {
logger.error(JSON.toJSONString(response));
}
}
@Override
public void onOperationFailed(NlsEvent e) {
logger.error("status code is {}, on operation failed: {}"+ e.getResponse().getStatusCode()+e.getErrorMessage());
}
@Override
public void onChannelClosed(NlsEvent e) {
logger.error("on websocket closed.");
}
@Override
public void run() {
init();
process();
shutDown();
}
}
這樣就能夠了，先啓動服務端，而後啓動app就能夠實現語音是說轉文字了哦服務器
補充代碼websocket
<?xml version="1.0" encoding="utf-8"?>
<RelativeLayout xmlns:android="http://schemas.android.com/apk/res/android"
xmlns:tools="http://schemas.android.com/tools"
android:id="@+id/activity_main"
android:layout_width="match_parent"
android:layout_height="match_parent"
android:paddingBottom="@dimen/activity_vertical_margin"
android:paddingLeft="@dimen/activity_horizontal_margin"
android:paddingRight="@dimen/activity_horizontal_margin"
android:paddingTop="@dimen/activity_vertical_margin"
tools:context="com.hht.myapplication.MainActivity">
<TextView
android:text=""
android:layout_width="wrap_content"
android:layout_height="wrap_content"
android:id="@+id/textView2"
android:maxLines="5"
android:layout_alignParentTop="true"
android:layout_alignParentStart="true" />
<TextView
android:text=""
android:layout_width="wrap_content"
android:layout_height="wrap_content"
android:textIsSelectable="true"
android:focusable="true"
android:layout_centerVertical="true"
android:layout_alignParentStart="true"
android:scrollbars="vertical"
android:maxLines="15"
android:fadeScrollbars="false"
android:id="@+id/textView" />
<Button
android:layout_width="fill_parent"
android:layout_height="wrap_content"
android:onClick="onClickCopy"
android:text="複製上面的文本內容"
android:id="@+id/button"
android:layout_marginBottom="12dp"
android:layout_alignParentBottom="true"
android:layout_alignParentEnd="true"
android:layout_marginEnd="7dp" />
</RelativeLayout>
相關文章
- 1. android 語音轉換文字（科大訊飛SDK簡易封裝）
- 2. Android 科大訊飛語音集成，文字轉語音
- 3. 文字轉換成語音，這裏有簡單的方法
- 4. 訊飛語音集成（語音轉文字，文字轉語音）
- 5. 科大訊飛實現「文字轉語音」和「語音轉文字」
- 6. 科大訊飛語音合成實例
- 7. 科大訊飛語音合成Demo講講（作作玩，超簡）
- 8. Java實現科大訊飛語音轉文字
- 9. 訊飛文字轉語音
- 10. Android Studio 接入 訊飛 語音合成（文字轉語音）
- 更多相關文章...
- • Scala 函數柯里化(Currying) - Scala教程
- • XSLT - 轉換 - XSLT 教程
- • 使用阿里雲OSS+CDN部署前端頁面與加速靜態資源
- • Git可視化極簡易教程 — Git GUI使用方法
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
歡迎關注本站公眾號,獲取更多信息
