java 音色识别_Java实现Shazam声音识别算法

Shazam算法采用傅里叶变换将时域信号转换为频域信号，并获得音频指纹，最后匹配指纹契合度来识别音频。

1、AudioSystem获取音频

奈奎斯特-香农采样定理告诉我们，为了能捕获人类能听到的声音频率，我们的采样速率必须是人类听觉范围的两倍。人类能听到的声音频率范围大约在20Hz到20000Hz之间，所以在录制音频的时候采样率大多是44100Hz。这是大多数标准MPEG-1 的采样率。44100这个值最初来源于索尼，因为它可以允许音频在修改过的视频设备上以25帧(PAL)或者30帧( NTSC)每秒进行录制，而且也覆盖了专业录音设备的20000Hz带宽。所以当你在选择录音的频率时，选择44100Hz就好了。

定义音频格式：

public static float sampleRate = 44100;

public static int sampleSizeInBits = 16;

public static int channels = 2; // double

public static boolean signed = true; // Indicates whether the data is signed or unsigned

public static boolean bigEndian = true; // Indicates whether the audio data is stored in big-endian or little-endian order

public AudioFormat getFormat() {

return new AudioFormat(sampleRate, sampleSizeInBits, channels, signed,

bigEndian);

}

调用麦克风获取音频，保存到out中

public static ByteArrayOutputStream out = new ByteArrayOutputStream();1

try {

AudioFormat format = smartAuto.getFormat(); // Fill AudioFormat with the settings

DataLine.Info info = new DataLine.Info(TargetDataLine.class, format);

startTime = new Date().getTime();

System.out.println(startTime);

SmartAuto.line = (TargetDataLine) AudioSystem.getLine(info);

SmartAuto.line.open(format);

SmartAuto.line.start();

new FileAnalysis().getDataToOut("");

while (smartAuto.running) {

checkTime(startTime);

}

SmartAuto.line.stop();

SmartAuto.line.close();

} catch (Throwable e) {

e.printStackTrace();

}

获取到的out数据需要通过傅里叶变换，从时域信号转换为频域信号。

傅里叶变换

public Complex[] fft(Complex[] x) {

int n = x.length;

// 因为exp(-2i*n*PI)=1，n=1时递归原点

if (n == 1){

return x;

}

// 如果信号数为奇数，使用dft计算

if (n % 2 != 0) {

return dft(x);

}

// 提取下标为偶数的原始信号值进行递归fft计算

Complex[] even = new Complex[n / 2];

for (int k = 0; k < n / 2; k++) {

even[k] = x[2 * k];

}

Complex[] evenValue = fft(even);

// 提取下标为奇数的原始信号值进行fft计算

// 节约内存

Complex[] odd = even;

for (int k = 0; k < n / 2; k++) {

odd[k] = x[2 * k + 1];

}

Complex[] oddValue = fft(odd);

// 偶数+奇数

Complex[] result = new Complex[n];

for (int k = 0; k < n / 2; k++) {

// 使用欧拉公式e^(-i*2pi*k/N) = cos(-2pi*k/N) + i*sin(-2pi*k/N)

double p = -2 * k * Math.PI / n;

Complex m = new Complex(Math.cos(p), Math.sin(p));

result[k] = evenValue[k].add(m.multiply(oddValue[k]));

// exp(-2*(k+n/2)*PI/n) 相当于 -exp(-2*k*PI/n)，其中exp(-n*PI)=-1(欧拉公式);

result[k + n / 2] = evenValue[k].subtract(m.multiply(oddValue[k]));

}

return result;

}

计算out的频域值

private void setFFTResult(){

byte audio[] = SmartAuto.out.toByteArray();

final int totalSize = audio.length;

System.out.println("totalSize = " + totalSize);

int chenkSize = 4;

int amountPossible = totalSize/chenkSize;

//When turning into frequency domain we'll need complex numbers:

SmartAuto.results = new Complex[amountPossible][];

DftOperate dfaOperate = new DftOperate();

//For all the chunks:

for(int times = 0;times < amountPossible; times++) {

Complex[] complex = new Complex[chenkSize];

for(int i = 0;i < chenkSize;i++) {

//Put the time domain data into a complex number with imaginary part as 0:

complex[i] = new Complex(audio[(times*chenkSize)+i], 0);

}

//Perform FFT analysis on the chunk:

SmartAuto.results[times] = dfaOperate.fft(complex);

}

System.out.println("results = " + SmartAuto.results.toString());

}