使用 FFT 和 Complex 类获取频率 wav 音频 [英] Get frequency wav audio using FFT and Complex class
本文介绍了使用 FFT 和 Complex 类获取频率 wav 音频的处理方法，对大家解决问题具有一定的参考价值，需要的朋友们下面随着小编来一起学习吧！
问题描述
问了很多，但我仍然坚持在Android上实现FFT类我需要使用 FFT 处理我的音频数据...
It's been asked a lot, but I still stuck about implement FFT class on Android I need to process my audio data using FFT...
我已经在这里阅读了几乎相同的问题如何我可以使用 FFT 从 PCM 获取频率数据吗在这里如何从fft结果中获取频率?还有更多的问题，但即使在我尝试给出的答案之后仍然找不到答案......
I already read the almost same question here How can I get frequency data from PCM using FFT and here How to get frequency from fft result? and more questions but still find no answer even after I tried the answers given...
我正在使用的 FFT 类:http://www.cs.princeton.edu/introcs/97data/FFT.java
FFT Class I'm using: http://www.cs.princeton.edu/introcs/97data/FFT.java
与之配套的复杂类:http://introcs.cs.princeton.edu/java/97data/Complex.java.html
这是我的代码
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import android.app.Activity;
import android.app.AlertDialog;
import android.content.DialogInterface;
import android.media.AudioFormat;
import android.media.AudioRecord;
import android.media.MediaRecorder;
import android.os.Bundle;
import android.os.Environment;
import android.view.View;
import android.widget.Button;
public class Latihan extends Activity{
private static final int RECORDER_BPP = 16;
private static final String AUDIO_RECORDER_FILE_EXT_WAV = ".wav";
private static final String AUDIO_RECORDER_FOLDER = "AudioRecorder";
private static final String AUDIO_RECORDER_TEMP_FILE = "record_temp.raw";
private static final int RECORDER_SAMPLERATE = 44100;
private static final int RECORDER_CHANNELS = AudioFormat.CHANNEL_IN_STEREO;
private static final int RECORDER_AUDIO_ENCODING = AudioFormat.ENCODING_PCM_16BIT;
short[] audioData;
private AudioRecord recorder = null;
private int bufferSize = 0;
private Thread recordingThread = null;
private boolean isRecording = false;
Complex[] fftTempArray;
Complex[] fftArray;
int[] bufferData;
int bytesRecorded;
@Override
public void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
setContentView(R.layout.p1);
setButtonHandlers();
enableButtons(false);
bufferSize = AudioRecord.getMinBufferSize
(RECORDER_SAMPLERATE,RECORDER_CHANNELS,RECORDER_AUDIO_ENCODING)*3;
audioData = new short [bufferSize]; //short array that pcm data is put into.
}
private void setButtonHandlers() {
((Button)findViewById(R.id.btStart)).setOnClickListener(btnClick);
((Button)findViewById(R.id.btStop)).setOnClickListener(btnClick);
}
private void enableButton(int id,boolean isEnable){
((Button)findViewById(id)).setEnabled(isEnable);
}
private void enableButtons(boolean isRecording) {
enableButton(R.id.btStart,!isRecording);
enableButton(R.id.btStop,isRecording);
}
private String getFilename(){
String filepath = Environment.getExternalStorageDirectory().getPath();
File file = new File(filepath,AUDIO_RECORDER_FOLDER);
if(!file.exists()){
file.mkdirs();
}
return (file.getAbsolutePath() + "/" + System.currentTimeMillis() + AUDIO_RECORDER_FILE_EXT_WAV);
}
public void convert(){
}
public void calculate(){
Complex[] fftTempArray = new Complex[bufferSize];
for (int i=0; i<bufferSize; i++)
{
fftTempArray[i] = new Complex(audioData[i], 0);
}
Complex[] fftArray = FFT.fft(fftTempArray);
double[] micBufferData = new double[bufferSize];
final int bytesPerSample = 2;
final double amplification = 100.0;
for (int index = 0, floatIndex = 0; index < bytesRecorded - bytesPerSample + 1; index += bytesPerSample, floatIndex++) {
double sample = 0;
for (int b = 0; b < bytesPerSample; b++) {
int v = bufferData[index + b];
if (b < bytesPerSample - 1 || bytesPerSample == 1) {
v &= 0xFF;
}
sample += v << (b * 8);
}
double sample32 = amplification * (sample / 32768.0);
micBufferData[floatIndex] = sample32;
}
}
private String getTempFilename(){
String filepath = Environment.getExternalStorageDirectory().getPath();
File file = new File(filepath,AUDIO_RECORDER_FOLDER);
if(!file.exists()){
file.mkdirs();
}
File tempFile = new File(filepath,AUDIO_RECORDER_TEMP_FILE);
if(tempFile.exists())
tempFile.delete();
return (file.getAbsolutePath() + "/" + AUDIO_RECORDER_TEMP_FILE);
}
private void startRecording(){
recorder = new AudioRecord(MediaRecorder.AudioSource.MIC,
RECORDER_SAMPLERATE, RECORDER_CHANNELS,RECORDER_AUDIO_ENCODING, bufferSize);
recorder.startRecording();
isRecording = true;
recordingThread = new Thread(new Runnable() {
public void run() {
writeAudioDataToFile();
}
},"AudioRecorder Thread");
recordingThread.start();
}
private void writeAudioDataToFile(){
byte data[] = new byte[bufferSize];
String filename = getTempFilename();
FileOutputStream os = null;
try {
os = new FileOutputStream(filename);
} catch (FileNotFoundException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
int read = 0;
if(null != os){
while(isRecording){
read = recorder.read(data, 0, bufferSize);
if(AudioRecord.ERROR_INVALID_OPERATION != read){
try {
os.write(data);
} catch (IOException e) {
e.printStackTrace();
}
}
}
try {
os.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
private void stopRecording(){
if(null != recorder){
isRecording = false;
recorder.stop();
recorder.release();
recorder = null;
recordingThread = null;
}
copyWaveFile(getTempFilename(),getFilename());
// deleteTempFile();
}
private void deleteTempFile() {
File file = new File(getTempFilename());
file.delete();
}
private void copyWaveFile(String inFilename,String outFilename){
FileInputStream in = null;
FileOutputStream out = null;
long totalAudioLen = 0;
long totalDataLen = totalAudioLen + 36;
long longSampleRate = RECORDER_SAMPLERATE;
int channels = 2;
long byteRate = RECORDER_BPP * RECORDER_SAMPLERATE * channels/8;
byte[] data = new byte[bufferSize];
try {
in = new FileInputStream(inFilename);
out = new FileOutputStream(outFilename);
totalAudioLen = in.getChannel().size();
totalDataLen = totalAudioLen + 36;
AppLog.logString("File size: " + totalDataLen);
WriteWaveFileHeader(out, totalAudioLen, totalDataLen,
longSampleRate, channels, byteRate);
while(in.read(data) != -1){
out.write(data);
}
in.close();
out.close();
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
private void WriteWaveFileHeader(
FileOutputStream out, long totalAudioLen,
long totalDataLen, long longSampleRate, int channels,
long byteRate) throws IOException {
//another code
}
private View.OnClickListener btnClick = new View.OnClickListener() {
public void onClick(View v) {
switch(v.getId()){
case R.id.btStart:{
AppLog.logString("Start Recording");
enableButtons(true);
startRecording();
break;
}
case R.id.btStop:{
AppLog.logString("Stop Recording");
enableButtons(false);
stopRecording();
calculate();
break;
}
}
}
};
}
我假设 audioData 数组包含原始音频数据，但我的代码捕获异常并返回N 不是 2 的幂"
I assume the audioData array contains the raw audio data,but my code catch the exception and return "N is not a power of 2"
我的代码有问题吗??我如何将它传递给 FFT.java 类并获得 fftResult ??
Is it anything wrong with my code ?? How do I pass it to FFT.java class and get the fftResult ??
或者有其他更简单的方法将时域数据转换为频率数据吗?
Or is there an other way to convert time domain data to frequency data that more easier ?
我已经有几个月没被这个问题困扰了......我的项目太比较 *.wav 文件的 2 个音频，任何帮助将不胜感激... :)
It's been a few months since I get stuck with this... My project is too compare 2 audio of *.wav files, Any help would be appreciated... :)
推荐答案
我已经找到了答案... :)
I already found the answer... :)
我创建了从音频计算数组值的方法...
I create method to calculate array value from audio...
public double[] calculateFFT(byte[] signal)
{
final int mNumberOfFFTPoints =1024;
double mMaxFFTSample;
double temp;
Complex[] y;
Complex[] complexSignal = new Complex[mNumberOfFFTPoints];
double[] absSignal = new double[mNumberOfFFTPoints/2];
for(int i = 0; i < mNumberOfFFTPoints; i++){
temp = (double)((signal[2*i] & 0xFF) | (signal[2*i+1] << 8)) / 32768.0F;
complexSignal[i] = new Complex(temp,0.0);
}
y = FFT.fft(complexSignal); // --> Here I use FFT class
mMaxFFTSample = 0.0;
mPeakPos = 0;
for(int i = 0; i < (mNumberOfFFTPoints/2); i++)
{
absSignal[i] = Math.sqrt(Math.pow(y[i].re(), 2) + Math.pow(y[i].im(), 2));
if(absSignal[i] > mMaxFFTSample)
{
mMaxFFTSample = absSignal[i];
mPeakPos = i;
}
}
return absSignal;
}
然后我在类 Write Audio 中调用它..
Then I called it in class Write Audio..
private void writeAudioDataToFile(){
byte data[] = new byte[bufferSize];
String filename = getTempFilename();
FileOutputStream os = null;
try {
os = new FileOutputStream(filename);
} catch (FileNotFoundException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
int read = 0;
if(null != os){
while(isRecording){
read = recorder.read(data, 0, bufferSize);
if(read > 0){
absNormalizedSignal = calculateFFT(data); // --> HERE ^__^
}
if(AudioRecord.ERROR_INVALID_OPERATION != read){
try {
os.write(data);
} catch (IOException e) {
e.printStackTrace();
}
}
}
try {
os.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}
这篇关于使用 FFT 和 Complex 类获取频率 wav 音频的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
查看全文
