java实现语音识别功能_Java实现的百度语音识别功能示例

本文实例讲述了Java实现的百度语音识别功能。分享给大家供大家参考,具体如下:

SDK以及示例代码下载地址: http://yuyin.baidu.com/sdk

最近一直在搞java,就选择了java工程。将代码拷过去。同时复制文件“test.pcm”到工程目录下。就基本上可以了。

注:test.pcm是语音文件,可以用audacity软件打开,选择 文件->导入->裸数据。 设置采样率为8000Hz。点击播放就能听见声音了。

这个时候程序跑起来还有问题,需要将apiKey 以及secretKey填写上。这两个值是你申请应用对应的分配好的。

cuid填本机mac地址就可以了,这个值我试过好像无所谓没啥要求。

程序能跑起来,并且按照正常返回识别的语音结果。但是返回结果的编码为GBK,所以汉字显示为乱码,需要对其进行一次转码。转码的代码是我自己加上去的。

下面贴代码:

package com.baidu.speech.serviceapi;

import java.io.BufferedReader;

import java.io.DataOutputStream;

import java.io.File;

import java.io.FileInputStream;

import java.io.IOException;

import java.io.InputStream;

import java.io.InputStreamReader;

import java.io.UnsupportedEncodingException;

import java.net.HttpURLConnection;

import java.net.URL;

import java.net.URLDecoder;

import java.net.URLEncoder;

import javax.xml.bind.DatatypeConverter;

import org.json.JSONObject;

public class Sample {

private static final String serverURL = "http://vop.baidu.com/server_api";

private static String token = "";

private static final String testFileName = "test.pcm"; // 百度语音提供技术支持

//put your own params here

// 下面3个值要填写自己申请的app对应的值

private static final String apiKey = "";

private static final String secretKey = "";

private static final String cuid = "";

public static void main(String[] args) throws Exception {

getToken();

method1();

method2();

}

private static void getToken() throws Exception {

String getTokenURL = "https://openapi.baidu.com/oauth/2.0/token?grant_type=client_credentials" +

"&client_id=" + apiKey + "&client_secret=" + secretKey;

HttpURLConnection conn = (HttpURLConnection) new URL(getTokenURL).openConnection();

token = new JSONObject(printResponse(conn)).getString("access_token");

}

private static void method1() throws Exception {

File pcmFile = new File(testFileName);

HttpURLConnection conn = (HttpURLConnection) new URL(serverURL).openConnection();

// construct params

JSONObject params = new JSONObject();

params.put("format", "pcm");

params.put("rate", 8000);

params.put("channel", "1");

params.put("token", token);

params.put("lan", "zh");

params.put("cuid", cuid);

params.put("len", pcmFile.length());

params.put("speech", DatatypeConverter.printBase64Binary(loadFile(pcmFile)));

// add request header

conn.setRequestMethod("POST");

conn.setRequestProperty("Content-Type", "application/json; charset=utf-8");

conn.setDoInput(true);

conn.setDoOutput(true);

// send request

DataOutputStream wr = new DataOutputStream(conn.getOutputStream());

wr.writeBytes(params.toString());

wr.flush();

wr.close();

printResponse(conn);

}

private static void method2() throws Exception {

File pcmFile = new File(testFileName);

HttpURLConnection conn = (HttpURLConnection) new URL(serverURL

+ "?cuid=" + cuid + "&token=" + token).openConnection();

// add request header

conn.setRequestMethod("POST");

conn.setRequestProperty("Content-Type", "audio/pcm; rate=8000");

conn.setDoInput(true);

conn.setDoOutput(true);

// send request

DataOutputStream wr = new DataOutputStream(conn.getOutputStream());

wr.write(loadFile(pcmFile));

wr.flush();

wr.close();

System.out.println(getUtf8String(printResponse(conn)));

}

private static String printResponse(HttpURLConnection conn) throws Exception {

if (conn.getResponseCode() != 200) {

// request error

System.out.println("conn.getResponseCode() = " + conn.getResponseCode());

return "";

}

InputStream is = conn.getInputStream();

BufferedReader rd = new BufferedReader(new InputStreamReader(is));

String line;

StringBuffer response = new StringBuffer();

while ((line = rd.readLine()) != null) {

response.append(line);

response.append('\r');

}

rd.close();

System.out.println(new JSONObject(response.toString()).toString(4));

return response.toString();

}

private static byte[] loadFile(File file) throws IOException {

InputStream is = new FileInputStream(file);

long length = file.length();

byte[] bytes = new byte[(int) length];

int offset = 0;

int numRead = 0;

while (offset < bytes.length

&& (numRead = is.read(bytes, offset, bytes.length - offset)) >= 0) {

offset += numRead;

}

if (offset < bytes.length) {

is.close();

throw new IOException("Could not completely read file " + file.getName());

}

is.close();

return bytes;

}

// GBK编码转为UTF-8

private static String getUtf8String(String s) throws UnsupportedEncodingException

{

StringBuffer sb = new StringBuffer();

sb.append(s);

String xmlString = "";

String xmlUtf8 = "";

xmlString = new String(sb.toString().getBytes("GBK"));

xmlUtf8 = URLEncoder.encode(xmlString , "GBK");

return URLDecoder.decode(xmlUtf8, "UTF-8");

}

}

更多java相关内容感兴趣的读者可查看本站专题:《Java面向对象程序设计入门与进阶教程》、《Java数据结构与算法教程》、《Java操作DOM节点技巧总结》、《Java文件与目录操作技巧汇总》和《Java缓存操作技巧汇总》

希望本文所述对大家java程序设计有所帮助。

你可能感兴趣的:(java实现语音识别功能)