如何在Android上检测声音频率?

时间:2014-09-19 10:09:55

标签: java android fft frequency frequency-analysis

首先,我对Android很新。在此之前我正在做Arduino。我想实现的第一个目标是能够检测特定的声音频率或模式。

因此,在我甚至可以检测到特定的声音频率之前,我必须能够至少看到所有频率。

在没有尝试的情况下,任何人都可以将此标记为重复或问题。我尽我所能,尽力而为。我几乎无法理解FFT如何工作或零交叉工作。但我已经读到过零交叉并不那么准确。所以,我正在使用FFT。我在这里非常密切地关注这篇文章,但我不知道整个工作代码是怎么样的。

Android audio FFT to retrieve specific frequency magnitude using audiorecord

所以,我尝试将问题和解决方案结合起来,如下面的代码所示。我几乎无法理解发生了什么。

FrequencyThread.java

package com.example.syahmul.backgroundapp;

/**
 * Record and detect frequency using FFT
 * Ref: https://stackoverflow.com/questions/5774104/android-audio-fft-to-retrieve-specific-frequency-
 * magnitude-using-audiorecord
 */

 //Audio Library
 import android.media.AudioRecord;
 import android.media.MediaRecorder.AudioSource;
 import android.media.AudioFormat;
 import android.provider.MediaStore;
 import android.util.Log;

public class FrequencyThread extends Thread{
    protected static final String TAG = "FrequencyThread";
    int channel_config = AudioFormat.CHANNEL_IN_MONO;
    int format = AudioFormat.ENCODING_PCM_16BIT;
    public int sampleSize = 8000;
    //public int bufferSize = AudioRecord.getMinBufferSize(sampleSize, channel_config, format); //640
public int bufferSize = 1024; //hardcode this so that can get power of 2
AudioRecord audioInput = new AudioRecord(AudioSource.MIC, sampleSize, channel_config, format, bufferSize);

private double ComputeFrequency(int arrayIndex) {
    //return ((1.0 * sampleRate) / (1.0 * fftOutWindowSize)) * arrayIndex;
    return ((1.0 * sampleSize) / (1.0 * bufferSize)) * arrayIndex;
}

@Override
public void run() {
    Log.i(TAG, "bufferSize: " + String.valueOf(bufferSize));

    //Read audio
    byte[] audioBuffer = new byte[bufferSize]; //short
    audioInput.startRecording();
    audioInput.read(audioBuffer, 0, bufferSize);
    int bytesRecorded = audioBuffer.length;
    Log.i(TAG, "bytesRecorded: " + String.valueOf(bytesRecorded));

    double[] micBufferData = new double[bufferSize];
    final int bytesPerSample = 2; // As it is 16bit PCM
    final double amplification = 100.0; // choose a number as you like
    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];
            int v = audioBuffer[index + b]; //what the hell is bufferData??
            if (b < bytesPerSample - 1 || bytesPerSample == 1) {
                v &= 0xFF;
            }
            sample += v << (b * 8);
        }
        double sample32 = amplification * (sample / 32768.0);
        micBufferData[floatIndex] = sample32;
        //Log.i(TAG, "micBufferData[" + floatIndex + "]: " + String.valueOf(micBufferData[floatIndex]));
    }

    Log.i(TAG, "Before feeing complex array with micbufferdata");

    //Feed complex Array with micBufferData
    Complex[] fftTempArray = new Complex[bufferSize];
    for (int i=0; i<bufferSize; i++) {
        fftTempArray[i] = new Complex(micBufferData[i], 0); //audio - micBufferData is empty!!
        Log.i(TAG, "fftTempArray[" + i + "]: " + String.valueOf(fftTempArray[i]));
    }

    Log.i(TAG, "fftTempArray length: " + String.valueOf(fftTempArray.length));
    //Complex[] fftArray = fft(fftTempArray);
    Complex[] fftArray = FFT.fft(fftTempArray); //this one is the cause of the crash. N is not
    //a power of 2
    for (int a=0; a<fftArray.length; a++) {
        //The frequency below make no sense!! Why is it sequential?
        Log.i(TAG, "computerFrequency: " + String.valueOf(ComputeFrequency(a)));
    }
  }
}

FFT.java

/*************************************************************************
 *  Compilation:  javac FFT.java
 *  Execution:    java FFT N
 *  Dependencies: Complex.java
 *
 *  Compute the FFT and inverse FFT of a length N complex sequence.
 *  Bare bones implementation that runs in O(N log N) time. Our goal
 *  is to optimize the clarity of the code, rather than performance.
 *
 *  Limitations
 *  -----------
 *   -  assumes N is a power of 2
 *
 *   -  not the most memory efficient algorithm (because it uses
 *      an object type for representing complex numbers and because
 *      it re-allocates memory for the subarray, instead of doing
 *      in-place or reusing a single temporary array)
 *
 *************************************************************************/
package com.example.syahmul.backgroundapp;

import android.util.Log;

import static android.util.Log.i;

public class FFT {
    protected static final String TAG = "FFT";

    // compute the FFT of x[], assuming its length is a power of 2
    public static Complex[] fft(Complex[] x) {
        int N = x.length;
        //int N = 1024; //I add this myself. To reflect power of 2. It did'nt work either
        Log.i(TAG, "N: " + String.valueOf(N));

    // base case
    if (N == 1) {
        Log.i(TAG, "N == 1 ");
        return new Complex[]{x[0]};
    }

    // radix 2 Cooley-Tukey FFT

    if (N % 2 != 0) {
        Log.i(TAG, "N%2 != 0"); //It only executed once
        throw new RuntimeException("N is not a power of 2");
    }

    // fft of even terms
    Complex[] even = new Complex[N/2];
    Log.i(TAG, "even length: " + even.length); //It only executed once
    for (int k = 0; k < N/2; k++) {
        even[k] = x[2*k];
    }
    Complex[] q = fft(even);

    // fft of odd terms
    Complex[] odd  = even;  // reuse the array
    for (int k = 0; k < N/2; k++) {
        odd[k] = x[2*k + 1];
    }
    Complex[] r = fft(odd);

    // combine
    Complex[] y = new Complex[N];
    for (int k = 0; k < N/2; k++) {
        double kth = -2 * k * Math.PI / N;
        Complex wk = new Complex(Math.cos(kth), Math.sin(kth));
        y[k]       = q[k].plus(wk.times(r[k]));
        y[k + N/2] = q[k].minus(wk.times(r[k]));
    }
    return y;
}


// compute the inverse FFT of x[], assuming its length is a power of 2
public static Complex[] ifft(Complex[] x) {
    int N = x.length;
    Complex[] y = new Complex[N];

    // take conjugate
    for (int i = 0; i < N; i++) {
        y[i] = x[i].conjugate();
    }

    // compute forward FFT
    y = fft(y);

    // take conjugate again
    for (int i = 0; i < N; i++) {
        y[i] = y[i].conjugate();
    }

    // divide by N
    for (int i = 0; i < N; i++) {
        y[i] = y[i].times(1.0 / N);
    }

    return y;

}

// compute the circular convolution of x and y
public static Complex[] cconvolve(Complex[] x, Complex[] y) {

    // should probably pad x and y with 0s so that they have same length
    // and are powers of 2
    if (x.length != y.length) { throw new RuntimeException("Dimensions don't agree"); }

    int N = x.length;

    // compute FFT of each sequence
    Complex[] a = fft(x);
    Complex[] b = fft(y);

    // point-wise multiply
    Complex[] c = new Complex[N];
    for (int i = 0; i < N; i++) {
        c[i] = a[i].times(b[i]);
    }

    // compute inverse FFT
    return ifft(c);
}


// compute the linear convolution of x and y
public static Complex[] convolve(Complex[] x, Complex[] y) {
    Complex ZERO = new Complex(0, 0);

    Complex[] a = new Complex[2*x.length];
    for (int i = 0;        i <   x.length; i++) a[i] = x[i];
    for (int i = x.length; i < 2*x.length; i++) a[i] = ZERO;

    Complex[] b = new Complex[2*y.length];
    for (int i = 0;        i <   y.length; i++) b[i] = y[i];
    for (int i = y.length; i < 2*y.length; i++) b[i] = ZERO;

    return cconvolve(a, b);
}

// display an array of Complex numbers to standard output
public static void show(Complex[] x, String title) {
    System.out.println(title);
    System.out.println("-------------------");
    for (int i = 0; i < x.length; i++) {
        System.out.println(x[i]);
    }
    System.out.println();
}


/*********************************************************************
 *  Test client and sample execution
 *
 *  % java FFT 4
 *  x
 *  -------------------
 *  -0.03480425839330703
 *  0.07910192950176387
 *  0.7233322451735928
 *  0.1659819820667019
 *
 *  y = fft(x)
 *  -------------------
 *  0.9336118983487516
 *  -0.7581365035668999 + 0.08688005256493803i
 *  0.44344407521182005
 *  -0.7581365035668999 - 0.08688005256493803i
 *
 *  z = ifft(y)
 *  -------------------
 *  -0.03480425839330703
 *  0.07910192950176387 + 2.6599344570851287E-18i
 *  0.7233322451735928
 *  0.1659819820667019 - 2.6599344570851287E-18i
 *
 *  c = cconvolve(x, x)
 *  -------------------
 *  0.5506798633981853
 *  0.23461407150576394 - 4.033186818023279E-18i
 *  -0.016542951108772352
 *  0.10288019294318276 + 4.033186818023279E-18i
 *
 *  d = convolve(x, x)
 *  -------------------
 *  0.001211336402308083 - 3.122502256758253E-17i
 *  -0.005506167987577068 - 5.058885073636224E-17i
 *  -0.044092969479563274 + 2.1934338938072244E-18i
 *  0.10288019294318276 - 3.6147323062478115E-17i
 *  0.5494685269958772 + 3.122502256758253E-17i
 *  0.240120239493341 + 4.655566391833896E-17i
 *  0.02755001837079092 - 2.1934338938072244E-18i
 *  4.01805098805014E-17i
 *
 *********************************************************************/

public static void main(String[] args) {
    int N = Integer.parseInt(args[0]);
    Complex[] x = new Complex[N];

    // original data
    for (int i = 0; i < N; i++) {
        x[i] = new Complex(i, 0);
        x[i] = new Complex(-2*Math.random() + 1, 0);
    }
    show(x, "x");

    // FFT of original data
    Complex[] y = fft(x);
    show(y, "y = fft(x)");

    // take inverse FFT
    Complex[] z = ifft(y);
    show(z, "z = ifft(y)");

    // circular convolution of x with itself
    Complex[] c = cconvolve(x, x);
    show(c, "c = cconvolve(x, x)");

    // linear convolution of x with itself
    Complex[] d = convolve(x, x);
    show(d, "d = convolve(x, x)");
 }

}

Complex.java

/*************************************************************************
 *  Compilation:  javac Complex.java
 *  Execution:    java Complex
 *
 *  Data type for complex numbers.
 *
 *  The data type is "immutable" so once you create and initialize
 *  a Complex object, you cannot change it. The "final" keyword
 *  when declaring re and im enforces this rule, making it a
 *  compile-time error to change the .re or .im fields after
 *  they've been initialized.
 *
 *  % java Complex
 *  a            = 5.0 + 6.0i
 *  b            = -3.0 + 4.0i
 *  Re(a)        = 5.0
 *  Im(a)        = 6.0
 *  b + a        = 2.0 + 10.0i
 *  a - b        = 8.0 + 2.0i
 *  a * b        = -39.0 + 2.0i
 *  b * a        = -39.0 + 2.0i
 *  a / b        = 0.36 - 1.52i
 *  (a / b) * b  = 5.0 + 6.0i
 *  conj(a)      = 5.0 - 6.0i
 *  |a|          = 7.810249675906654
 *  tan(a)       = -6.685231390246571E-6 + 1.0000103108981198i
 *
 *************************************************************************/
package com.example.syahmul.backgroundapp;

public class Complex {
private final double re;   // the real part
private final double im;   // the imaginary part

// create a new object with the given real and imaginary parts
public Complex(double real, double imag) {
    re = real;
    im = imag;
}

// return a string representation of the invoking Complex object
public String toString() {
    if (im == 0) return re + "";
    if (re == 0) return im + "i";
    if (im <  0) return re + " - " + (-im) + "i";
    return re + " + " + im + "i";
}

// return abs/modulus/magnitude and angle/phase/argument
public double abs()   { return Math.hypot(re, im); }  // Math.sqrt(re*re + im*im)
public double phase() { return Math.atan2(im, re); }  // between -pi and pi

// return a new Complex object whose value is (this + b)
public Complex plus(Complex b) {
    Complex a = this;             // invoking object
    double real = a.re + b.re;
    double imag = a.im + b.im;
    return new Complex(real, imag);
}

// return a new Complex object whose value is (this - b)
public Complex minus(Complex b) {
    Complex a = this;
    double real = a.re - b.re;
    double imag = a.im - b.im;
    return new Complex(real, imag);
}

// return a new Complex object whose value is (this * b)
public Complex times(Complex b) {
    Complex a = this;
    double real = a.re * b.re - a.im * b.im;
    double imag = a.re * b.im + a.im * b.re;
    return new Complex(real, imag);
}

// scalar multiplication
// return a new object whose value is (this * alpha)
public Complex times(double alpha) {
    return new Complex(alpha * re, alpha * im);
}

// return a new Complex object whose value is the conjugate of this
public Complex conjugate() {  return new Complex(re, -im); }

// return a new Complex object whose value is the reciprocal of this
public Complex reciprocal() {
    double scale = re*re + im*im;
    return new Complex(re / scale, -im / scale);
}

// return the real or imaginary part
public double re() { return re; }
public double im() { return im; }

// return a / b
public Complex divides(Complex b) {
    Complex a = this;
    return a.times(b.reciprocal());
}

// return a new Complex object whose value is the complex exponential of this
public Complex exp() {
    return new Complex(Math.exp(re) * Math.cos(im), Math.exp(re) * Math.sin(im));
}

// return a new Complex object whose value is the complex sine of this
public Complex sin() {
    return new Complex(Math.sin(re) * Math.cosh(im), Math.cos(re) * Math.sinh(im));
}

// return a new Complex object whose value is the complex cosine of this
public Complex cos() {
    return new Complex(Math.cos(re) * Math.cosh(im), -Math.sin(re) * Math.sinh(im));
}

// return a new Complex object whose value is the complex tangent of this
public Complex tan() {
    return sin().divides(cos());
}



// a static version of plus
public static Complex plus(Complex a, Complex b) {
    double real = a.re + b.re;
    double imag = a.im + b.im;
    Complex sum = new Complex(real, imag);
    return sum;
}



// sample client for testing
public static void main(String[] args) {
    Complex a = new Complex(5.0, 6.0);
    Complex b = new Complex(-3.0, 4.0);

    System.out.println("a            = " + a);
    System.out.println("b            = " + b);
    System.out.println("Re(a)        = " + a.re());
    System.out.println("Im(a)        = " + a.im());
    System.out.println("b + a        = " + b.plus(a));
    System.out.println("a - b        = " + a.minus(b));
    System.out.println("a * b        = " + a.times(b));
    System.out.println("b * a        = " + b.times(a));
    System.out.println("a / b        = " + a.divides(b));
    System.out.println("(a / b) * b  = " + a.divides(b).times(b));
    System.out.println("conj(a)      = " + a.conjugate());
    System.out.println("|a|          = " + a.abs());
    System.out.println("tan(a)       = " + a.tan());
}

}

computeFrequency输出为0.0 - 7992.1875,依次增量为7.8125

0.0
7.8125
15.625
23.4375
31.25
39.0625
.
.
7992.1875

我硬编码了下面因为我不断得到&#34; N不是2的力量&#34;:

//public int bufferSize = AudioRecord.getMinBufferSize(sampleSize, channel_config, format); //640
 public int bufferSize = 1024; //hardcode this so that can get power of 2

确定。这完全是关于它的。我希望我在这里很清楚。请告诉我如何才能获得正确的频率。

此外,超出了这个问题的范围,我怎样才能在这样的情况下改变它,不断检测特定的频率。 :)

0 个答案:

没有答案