0
我的程序基本上是以語音轉文本。我正在使用LiveSpeechRecognizer CMU Sphinx。我的程序運行時沒有任何錯誤，但沒有打印文字。我的意思是它從我的語法文件中打印隨機單詞。LiveSpeechRecognizer打印隨機單詞
我用我的三星手機耳機作爲我的麥克風
代碼：
/*
* 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
我沒有說過這些話。請幫忙。
其對文字的講話。 –