JAVA做的语音识别 (via TranXcode)我想用java实现一个 语音识别的软件。比如我说一句‘hello’，软件就会采集
JAVA做的语音识别 (via TranXcode)
我想用java实现一个 语音识别的软件。比如我说一句‘hello’，软件就会采集我说话的特征值，并记录下来，并输出相应值。当别人说‘hello’的时候，采集其特征值，并与我的比较，相同就通过，不同就继续输入。声音的采集主要通过麦克风实现。
[解决办法]
声音识别是一个专门的技术，其实就是对声音波形的判断。如果你想用Java实现的话，那你必须先对Java的声音输入输出的操作有基本的了解。下面是一个简单的录音并输出的程序。录音的时候，每次读取数据是存放在buffer这个字节数组之中的，再把它输出。而你，是要识别的话，就是从这个数组中提取信息。那么这个数组的结构是什么样的呢。对这个程序而言，采用16位双声道录音，那么这个数组，每2位拼起来，是一个采样值，这个值即是声音的响度。将2个字节视为一个单位的话，由于是双声道，就是说，两个单位一组，一个是左声道，一个是右声道，交替录入的。
- Java code
import java.io.*;import javax.sound.sampled.AudioSystem;import javax.sound.sampled.AudioInputStream;import javax.sound.sampled.AudioFormat;import javax.sound.sampled.SourceDataLine;import javax.sound.sampled.DataLine;import javax.sound.sampled.FloatControl;import javax.sound.sampled.TargetDataLine;public class RecordAndPlay { volatile int divider; public RecordAndPlay(){ Play(); } public static void main(String[] args) { new RecordAndPlay(); } //播放音频文件 public void Play() { try { AudioFormat audioFormat =// new AudioFormat(AudioFormat.Encoding.PCM_SIGNED, 44100F,// 8, 1, 1, 44100F, false); new AudioFormat(AudioFormat.Encoding.PCM_SIGNED,44100F, 16, 2, 4, 44100F, true); DataLine.Info info = new DataLine.Info(TargetDataLine.class, audioFormat); TargetDataLine targetDataLine = (TargetDataLine) AudioSystem.getLine(info); targetDataLine.open(audioFormat); SourceDataLine sourceDataLine; info = new DataLine.Info(SourceDataLine.class, audioFormat); sourceDataLine = (SourceDataLine) AudioSystem.getLine(info); sourceDataLine.open(audioFormat); targetDataLine.start(); sourceDataLine.start(); FloatControl fc=(FloatControl)sourceDataLine.getControl(FloatControl.Type.MASTER_GAIN); double value=0.2; float dB = (float)(Math.log(value==0.0?0.0001:value)/Math.log(10.0)*20.0); fc.setValue(dB); int nByte = 0; final int bufSize=1024; byte[] buffer = new byte[bufSize]; while (nByte != -1) { //System.in.read(); nByte = targetDataLine.read(buffer, 0, bufSize); sourceDataLine.write(buffer, 0, nByte); } sourceDataLine.stop(); } catch (Exception e) { e.printStackTrace(); } }}
[解决办法]
那针对上次给你的那个录音程序，我写了一个录音并显示波形的程序。功能如下：
1.点击“开始”开始录音并显示，点击“暂停”即可暂停录音。
2.在暂停录音的状态下，可以移动滚动条查看之前的波形，按“回放”可以回放并显示波形，回放的开始是在当前显示的最左边的波形所对应的声音（不过这里遇到一个问题，即最后一点声音回放不出来，比较奇怪，没找到原因）。
程序如下：
- Java code
import java.awt.*;import java.awt.event.*;import java.awt.geom.Line2D;import javax.swing.*;import javax.swing.event.*;import java.util.*;import javax.sound.sampled.AudioSystem;import javax.sound.sampled.AudioInputStream;import javax.sound.sampled.AudioFormat;import javax.sound.sampled.SourceDataLine;import javax.sound.sampled.DataLine;import javax.sound.sampled.FloatControl;import javax.sound.sampled.TargetDataLine;/** * 2011-6-23 0:53:40 * @author Administrator */public class ShowWave { JFrame frame; JPanel pan; final int panHeight=400; JScrollBar timeLocationScrollBar; int point[]; int number; byte bufferAll[]; int bufferAllIndex; int vRate,hRate; JButton startButton,pauseButton; JButton replayButton,stopReplayButton; boolean continueRecorde; boolean continueReplay; JPanel centerPane,buttonPane; JSlider hSlider; boolean jsbActive; public ShowWave(){ initData(); frame=new JFrame("录音并显示波形"); pan=new JPanel(){ public void paint(Graphics g){ g.setColor(Color.WHITE); g.fillRect(0, 0, this.getWidth(), this.getHeight()); g.setColor(Color.red); int x[]=new int[number]; for(int i=0;i<number;i++){ x[i]=i; point[i]=panHeight-point[i]; } g.drawPolyline(x, point, number);// Graphics2D g2d=(Graphics2D)g;// for(int i=0;i<number-1;i++){// g2d.draw(new Line2D.Double(x[i], point[i], x[i+1], point[i+1]));// } g.setColor(Color.blue); } }; pan.setPreferredSize(new Dimension(600,panHeight)); timeLocationScrollBar=new JScrollBar(); timeLocationScrollBar.setOrientation(JScrollBar.HORIZONTAL); timeLocationScrollBar.setMaximum(0); timeLocationScrollBar.setMinimum(0); timeLocationScrollBar.setValue(0); timeLocationScrollBar.addAdjustmentListener(new AdjustmentListener() { public void adjustmentValueChanged(AdjustmentEvent e) { if(jsbActive==false){ return; } synchronized(bufferAll){ int beginIndex=timeLocationScrollBar.getValue(); beginIndex=beginIndex*2*hRate; if(beginIndex==0){ number=bufferAllIndex/hRate/2; if(number>600){ number=600; } } else{ number=600; } for(int i=0;i<number;i++,beginIndex+=2*hRate){ int hBit=bufferAll[beginIndex]; int lBit=bufferAll[beginIndex+1]; point[i]=hBit<<8|lBit; point[i]/=vRate; point[i]+=panHeight/2; } pan.repaint(); } } }); centerPane=new JPanel(); centerPane.setLayout(new BorderLayout()); centerPane.add(pan); centerPane.add(timeLocationScrollBar,BorderLayout.SOUTH); frame.getContentPane().add(centerPane); startButton=new JButton("开始"); startButton.addActionListener(new ActionListener() { public void actionPerformed(ActionEvent e) { continueRecorde=true; jsbActive=false; } }); pauseButton=new JButton("暂停"); pauseButton.addActionListener(new ActionListener() { public void actionPerformed(ActionEvent e) { continueRecorde=false; jsbActive=true; } }); hSlider=new JSlider(); hSlider.setOrientation(JSlider.HORIZONTAL); hSlider.setMaximum(100); hSlider.setMinimum(1); hSlider.setValue(hRate); hSlider.addChangeListener(new ChangeListener() { public void stateChanged(ChangeEvent e) { hRate=hSlider.getValue(); int length=bufferAllIndex/hRate/2; length-=600; int value=(int)((double)timeLocationScrollBar.getValue()/timeLocationScrollBar.getMaximum()*length); jsbActive=false; timeLocationScrollBar.setMaximum(length); jsbActive=true; timeLocationScrollBar.setValue(value); } }); replayButton=new JButton("回放"); replayButton.addActionListener(new ActionListener() { public void actionPerformed(ActionEvent e) { if(continueRecorde||continueReplay){ return; } new Thread(){ public void run(){ try{ continueReplay=true; AudioFormat audioFormat =new AudioFormat(AudioFormat.Encoding.PCM_SIGNED, 44100F, 16, 1, 2,44100F, true); DataLine.Info info = new DataLine.Info(SourceDataLine.class, audioFormat); SourceDataLine sourceDataLine; sourceDataLine = (SourceDataLine) AudioSystem.getLine(info); sourceDataLine.open(audioFormat); sourceDataLine.start(); FloatControl fc=(FloatControl)sourceDataLine.getControl(FloatControl.Type.MASTER_GAIN); double value=2; float dB = (float)(Math.log(value==0.0?0.0001:value)/Math.log(10.0)*20.0); fc.setValue(dB); int beginIndex=timeLocationScrollBar.getValue(); beginIndex=beginIndex*2*hRate; int bufSize=1024; byte buffer[]=new byte[bufSize]; while (beginIndex < bufferAllIndex && continueReplay) { synchronized (bufferAll) { int nByte = bufferAllIndex - beginIndex > bufSize ? bufSize : bufferAllIndex - beginIndex; System.arraycopy(bufferAll, beginIndex, buffer, 0, nByte); sourceDataLine.write(buffer, 0, nByte);// System.out.println(beginIndex+" "+bufferAllIndex); beginIndex += nByte; if(beginIndex/2/hRate<=timeLocationScrollBar.getMaximum()){ timeLocationScrollBar.setValue(beginIndex/2/hRate); } } } sourceDataLine.flush(); sourceDataLine.stop(); sourceDataLine.close(); continueReplay=false; }catch(Exception ee){ee.printStackTrace();} } }.start(); } }); stopReplayButton=new JButton("停止回放"); stopReplayButton.addActionListener(new ActionListener(){ public void actionPerformed(ActionEvent e) { continueReplay=false; } }); Box box=Box.createHorizontalBox(); box.add(Box.createHorizontalGlue()); box.add(startButton); box.add(Box.createHorizontalStrut(10)); box.add(pauseButton); box.add(Box.createHorizontalStrut(10)); box.add(hSlider); box.add(Box.createHorizontalStrut(10)); box.add(replayButton); box.add(Box.createHorizontalStrut(10)); box.add(stopReplayButton); box.add(Box.createHorizontalGlue()); box.setBorder(BorderFactory.createEmptyBorder(10, 10, 10, 10)); frame.getContentPane().add(box,BorderLayout.SOUTH); frame.pack(); frame.setLocationRelativeTo(null); frame.setDefaultCloseOperation(JFrame.EXIT_ON_CLOSE); frame.setVisible(true); play(); }