import com.baidu.aip.speech.AipSpeech;
import com.baidu.aip.speech.TtsResponse;
import com.baidu.aip.util.Util;
import javazoom.spi.mpeg.sampled.file.MpegAudioFileReader;
import lombok.extern.slf4j.Slf4j;
import org.json.JSONObject;
import javax.sound.sampled.AudioFileFormat;
import javax.sound.sampled.AudioFormat;
import javax.sound.sampled.AudioInputStream;
import javax.sound.sampled.AudioSystem;
import java.io.File;
import java.io.IOException;
/**
* @ProjectName: testPcm
* @Package: com.XXX.util
* @Author: huat
* @Date: 2019/8/10 12:20
* @Version: 1.0
*/
@Slf4j
public class chinese {
//设置APPID/AK/SK
public static final String APP_ID = "XXXXXXXXX";
public static final String API_KEY = "XXXXXXXXXXXXXx";
public static final String SECRET_KEY = "XXXXXXXXXXXXXXXXXXXx";
public static AipSpeech client = null;
/**
* 单例 懒加载模式 返回实例
* @return
*/
public static AipSpeech getInstance(){
if (client==null){
synchronized (AipSpeech.class){
if (client==null) {
client = new AipSpeech(APP_ID, API_KEY, SECRET_KEY);
}
}
}
return client;
}
/**
* 语音合成
* @param word 文字内容
* @param outputPath 合成语音生成路径
* @return
*/
public static boolean SpeechSynthesizer(String word, String outputPath) {
/*
最长的长度
*/
int maxLength = 1024;
if (word.getBytes().length >= maxLength) {
return false;
}
// 初始化一个AipSpeech
client = getInstance();
// 可选:设置网络连接参数
client.setConnectionTimeoutInMillis(2000);
client.setSocketTimeoutInMillis(60000);
// 可选:设置代理服务器地址, http和socket二选一,或者均不设置
// client.setHttpProxy("proxy_host", proxy_port); // 设置http代理
// client.setSocketProxy("proxy_host", proxy_port); // 设置socket代理
// 调用接口
TtsResponse res = client.synthesis(word, "zh", 1, null);
byte[] data = res.getData();
org.json.JSONObject res1 = res.getResult();
if (data != null) {
try {
Util.writeBytesToFileSystem(data, outputPath);
} catch (IOException e) {
e.printStackTrace();
}
return true;
}
if (res1 != null) {
log.info(" result : " + res1.toString());
}
return false;
}
/**
* 语音识别
* @param videoPath
* @param videoType
* @return
*/
public static String SpeechRecognition(String videoPath, String videoType) {
// 初始化一个AipSpeech
client = getInstance();
// 可选:设置网络连接参数
client.setConnectionTimeoutInMillis(2000);
client.setSocketTimeoutInMillis(60000);
// 可选:设置代理服务器地址, http和socket二选一,或者均不设置
// client.setHttpProxy("proxy_host", proxy_port); // 设置http代理
// client.setSocketProxy("proxy_host", proxy_port); // 设置socket代理
// 调用接口
JSONObject res = client.asr(videoPath, videoType, 16000, null);
log.info(" SpeechRecognition : " + res.toString());
return res.toString(2);
}
/**
* mp3转pcm
* @param mp3filepath MP3文件存放路径
* @param pcmfilepath pcm文件保存路径
* @return
*/
public static boolean convertMP32Pcm(String mp3filepath, String pcmfilepath){
try {
//获取文件的音频流,pcm的格式
AudioInputStream audioInputStream = getPcmAudioInputStream(mp3filepath);
//将音频转化为 pcm的格式保存下来
AudioSystem.write(audioInputStream, AudioFileFormat.Type.WAVE, new File(pcmfilepath));
return true;
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
return false;
}
}
/**
* 获得pcm文件的音频流
* @param mp3filepath
* @return
*/
private static AudioInputStream getPcmAudioInputStream(String mp3filepath) {
File mp3 = new File(mp3filepath);
AudioInputStream audioInputStream = null;
AudioFormat targetFormat = null;
try {
AudioInputStream in = null;
MpegAudioFileReader mp = new MpegAudioFileReader();
in = mp.getAudioInputStream(mp3);
AudioFormat baseFormat = in.getFormat();
targetFormat = new AudioFormat(AudioFormat.Encoding.PCM_SIGNED, baseFormat.getSampleRate(), 16,
baseFormat.getChannels(), baseFormat.getChannels()*2, baseFormat.getSampleRate(), false);
audioInputStream = AudioSystem.getAudioInputStream(targetFormat, in);
} catch (Exception e) {
e.printStackTrace();
}
return audioInputStream;
}
public static void main(String[] args) throws IOException {
// SpeechSynthesizer("简单测试百度语音合成", "d:/SpeechSynthesizer.mp3");
//mp3转pcm格式
convertMP32Pcm("E:/KwDownload/song/许嵩-有何不可 - 铃声.mp3","d:/16k.pcm");
//第二个参数为文件后缀
SpeechRecognition("d:/16k.pcm","pcm");
}
}