Java LiveSpeechRecognitor打印随机单词
我的程序基本上是从语音到文本的。我正在使用Java LiveSpeechRecognitor打印随机单词,java,speech-recognition,cmusphinx,Java,Speech Recognition,Cmusphinx,我的程序基本上是从语音到文本的。我正在使用LiveSpeechRecognizer CMU Sphinx。我的程序正在运行,没有任何错误,但它没有打印文字。我的意思是它从我的语法文件中随机打印单词 我用我的三星手机耳机作为麦克风 代码: /* * To change this license header, choose License Headers in Project Properties. * To change this template file, choose Tools |
LiveSpeechRecognizer CMU Sphinx
。我的程序正在运行,没有任何错误,但它没有打印文字。我的意思是它从我的语法文件中随机打印单词
我用我的三星手机耳机作为麦克风
代码:
/*
* To change this license header, choose License Headers in Project Properties.
* To change this template file, choose Tools | Templates
* and open the template in the editor.
*/
package SpeechRec;
import java.io.IOException;
import javax.sound.sampled.*;
import edu.cmu.sphinx.api.*;
/**
*
* @author divyanshu kunwar
*/
public class SpeechRec{
// Variables
private String result;
// Threads
Thread speechThread;
Thread resourcesThread;
// LiveRecognizer
private LiveSpeechRecognizer recognizer;
/**
* Constructor
*/
public SpeechRec() {
// Loading Message
// Configuration
Configuration configuration = new Configuration();
// Load model from the jar
configuration.setAcousticModelPath("resource:/edu/cmu/sphinx/models/en-us/en-us");
configuration.setDictionaryPath("resource:/edu/cmu/sphinx/models/en-us/cmudict-en-us.dict");
// if you want to use LanguageModelPath disable the 3 lines after which
// are setting a custom grammar->
// Grammar
configuration.setGrammarPath("resource:/grammars");
configuration.setGrammarName("grammar");
configuration.setUseGrammar(true);
try {
recognizer = new LiveSpeechRecognizer(configuration);
} catch (IOException ex) {
}
// Start recognition process pruning previously cached data.
recognizer.startRecognition(true);
// Start the Thread
startSpeechThread();
startResourcesThread();
}
/**
* Starting the main Thread of speech recognition
*/
protected void startSpeechThread() {
// alive?
if (speechThread != null && speechThread.isAlive())
return;
// initialise
speechThread = new Thread(() -> {
try {
while (true) {
/*
* This method will return when the end of speech is
* reached. Note that the end pointer will determine the end
* of speech.
*/
SpeechResult speechResult = recognizer.getResult();
if (speechResult != null) {
result = speechResult.getHypothesis();
System.out.println("You said: [" + result + "]\n");
// logger.log(Level.INFO, "You said: " + result + "\n")
} else{}
}
} catch (Exception ex) {
}
});
// Start
speechThread.start();
}
/**
* Starting a Thread that checks if the resources needed to the
* SpeechRecognition library are available
*/
protected void startResourcesThread() {
// alive?
if (resourcesThread != null && resourcesThread.isAlive())
return;
resourcesThread = new Thread(() -> {
try {
// Detect if the microphone is available
while (true) {
if (AudioSystem.isLineSupported(Port.Info.MICROPHONE)) {
// logger.log(Level.INFO, "Microphone is available.\n")
} else {
// logger.log(Level.INFO, "Microphone is not
// available.\n")
}
// Sleep some period
Thread.sleep(3500);
}
} catch (InterruptedException ex) {
resourcesThread.interrupt();
}
});
// Start
resourcesThread.start();
}
/**
* Takes a decision based on the given result
*/
public void makeDesicion(String result) {
//implemented in the part 2
}
/**
* Java Main Application Method
*
* @param args
*/
public static void main(String[] args) {
// // Be sure that the user can't start this application by not giving
// the
// // correct entry string
// if (args.length == 1 && "SPEECH".equalsIgnoreCase(args[0]))
new SpeechRec();
// else
// Logger.getLogger(Main.class.getName()).log(Level.WARNING, "Give me
// the correct entry string..");
}
}
Grammar File:
#JSGF V1.0;
grammar grammar;
public <numbers> = (one | two | three| four| five | six | seven | eight | nine | ten);
public <words>=(how | where);
Output:
You said: [one]
21:01:38.251 INFO liveCMN 35.23 -8.72 -11.38 11.38 2.68 -13.93 3.08 1.74 -8.43 -1.72 -0.49 -8.30 -3.83
21:01:38.519 INFO speedTracker This Time Audio: 0.76s Proc: 0.73s Speed: 0.96 X real time
21:01:38.519 INFO speedTracker Total Time Audio: 2.93s Proc: 0.99s 0.34 X real time
You said: [one]
21:01:38.519 INFO memoryTracker Mem Total: 434.00 Mb Free: 303.12 Mb
21:01:38.519 INFO memoryTracker Used: This: 130.88 Mb Avg: 124.48 Mb Max: 130.88 Mb
21:01:40.233 INFO speedTracker This Time Audio: 0.30s Proc: 0.19s Speed: 0.64 X real time
You said: [two]
21:01:40.233 INFO speedTracker Total Time Audio: 3.23s Proc: 1.18s 0.37 X real time
21:01:40.233 INFO memoryTracker Mem Total: 434.00 Mb Free: 295.40 Mb
21:01:40.233 INFO memoryTracker Used: This: 138.60 Mb Avg: 129.18 Mb Max: 138.60 Mb
21:01:41.777 INFO liveCMN 35.55 -8.33 -10.84 13.40 3.05 -13.95 4.24 1.77 -9.87 -2.61 -1.27 -8.00 -3.56
21:01:42.853 INFO liveCMN 35.35 -7.67 -10.27 11.74 2.97 -13.25 3.25 1.60 -9.12 -2.91 -1.70 -7.04 -3.10
21:01:42.990 INFO speedTracker This Time Audio: 1.29s Proc: 1.25s Speed: 0.97 X real time
21:01:42.990 INFO speedTracker Total Time Audio: 4.52s Proc: 2.43s 0.54 X real time
You said: [one]
21:01:42.990 INFO memoryTracker Mem Total: 434.00 Mb Free: 279.92 Mb
21:01:42.991 INFO memoryTracker Used: This: 154.08 Mb Avg: 135.41 Mb Max: 154.08 Mb
/*
*要更改此许可证标题,请在“项目属性”中选择“许可证标题”。
*要更改此模板文件,请选择工具|模板
*然后在编辑器中打开模板。
*/
一揽子演讲;
导入java.io.IOException;
导入javax.sound.sampled.*;
导入edu.cmu.sphinx.api.*;
/**
*
*@作者divyanshu kunwar
*/
公开课讲演{
//变数
私有字符串结果;
//线程
线程说线程;
线程资源线程;
//肝脏识别器
专用LiveSpeechRecognitor识别器;
/**
*建造师
*/
公众演讲{
//加载消息
//配置
配置=新配置();
//从jar加载模型
setAcousticModelPath(“资源:/edu/cmu/sphinx/models/en-us/en-us”);
setDictionaryPath(“resource:/edu/cmu/sphinx/models/en-us/cmudict en-us.dict”);
//如果要使用LanguageModelPath,请禁用后面的3行
//正在设置自定义语法->
//文法
setGrammarPath(“资源:/grammars”);
setGrammarName(“语法”);
setUseGrammar(true);
试一试{
识别器=新的LiveSpeechRecognizer(配置);
}捕获(IOEX异常){
}
//开始识别过程修剪以前缓存的数据。
识别器。startRecognition(真);
//开线
startSpeechThread();
startResourcesThread();
}
/**
*启动语音识别的主线
*/
受保护的void startSpeechThread(){
//活着?
if(speechThread!=null&&speechThread.isAlive())
返回;
//初始化
speechThread=新线程(()->{
试一试{
while(true){
/*
*此方法将在结束讲话时返回
*已到达。请注意,结束指针将确定结束
*说话的方式。
*/
SpeechResult SpeechResult=recognizer.getResult();
if(speechResult!=null){
结果=speechResult.gethyporation();
System.out.println(“您说过:[“+result+”]\n”);
//logger.log(Level.INFO,“您说:“+result+”\n”)
}else{}
}
}捕获(例外情况除外){
}
});
//开始
speechThread.start();
}
/**
*启动一个线程,该线程检查
*语音识别库可用
*/
受保护的void startResourcesThread(){
//活着?
if(resourcesThread!=null&&resourcesThread.isAlive()
返回;
resourcesThread=新线程(()->{
试一试{
//检测麦克风是否可用
while(true){
if(AudioSystem.isLineSupported(端口信息麦克风)){
//logger.log(Level.INFO,“麦克风可用。\n”)
}否则{
//logger.log(Level.INFO),“麦克风不可用
//可用。\n“
}
//睡一段时间
睡眠(3500);
}
}捕获(中断异常例外){
resourcesThread.interrupt();
}
});
//开始
resourcesThread.start();
}
/**
*根据给定的结果做出决定
*/
公共void makedecision(字符串结果){
//在第2部分中实现
}
/**
*Java主应用方法
*
*@param args
*/
公共静态void main(字符串[]args){
////确保用户不能通过不提供
//
////正确的输入字符串
//if(args.length==1&&“SPEECH.equalsIgnoreCase(args[0]))
新SpeechRec();
//否则
//Logger.getLogger(Main.class.getName()).log(Level.WARNING,“告诉我
//正确的输入字符串…);
}
}
语法文件:
#jsgfv1.0;
语法;
公共=(一|二|三|四|五|六|七|八|九|十);
public=(how | where);
输出:
你说:[一]
21:01:38.251信息直播CMN 35.23-8.72-11.38 11.38 2.68-13.93 3.08 1.74-8.43-1.72-0.49-8.30-3.83
21:01:38.519信息速度跟踪器这次音频:0.76s进程:0.73s速度:0.96 X实时
21:01:38.519信息速度跟踪器总时间音频:2.93s进程:0.99s 0.34 X实时
你说:[一]
21:01:38.519信息存储器Tracker Mem总计:434.00 Mb免费:303.12 Mb
21:01:38.519使用的信息内存跟踪程序:此:130.88 Mb平均:124.48 Mb最大:130.88 Mb
21:01:40.233信息速度跟踪器这次音频:0.30s进程:0.19s速度:0.64 X实时
你说:[两个]
21:01:40.233信息速度跟踪器总时间音频:3.23s过程:1.18s 0.37 X实时
21:01:40.233信息存储器Tracker Mem总计:434.00 Mb免费:295.40 Mb
21:01:40.233使用的信息内存跟踪程序:此:138.60 Mb平均:129.18 Mb最大:138.60 Mb
21:01:41.777信息直播CMN 35.55-8.33-10.84 13.40 3.05-13.95 4.24 1.77-9.87-2.61-1.27-8.00-3.56
21:01:42.853信息直播CMN 35.35-7.67-10.27 11.74 2.97-13.25 3.25 1.60-9.12-2.91-1.70-7.04-3.10
21:01:42.990信息速度跟踪器