annotate dsp/mfcc/MFCC.h @ 73:dcb555b90924

* Key detector: when returning key strengths, use the peak value of the
  three underlying chromagram correlations (from 36-bin chromagram)
  corresponding to each key, instead of the mean.
  Rationale: This is the same method as used when returning the key value,
  and it's nice to have the same results in both returned value and plot.
  The peak performed better than the sum with a simple test set of triads,
  so it seems reasonable to change the plot to match the key output rather
  than the other way around.

* FFT: kiss_fftr returns only the non-conjugate bins, synthesise the rest
  rather than leaving them (perhaps dangerously) undefined.  Fixes an
  uninitialised data error in chromagram that could cause garbage results
  from key detector.

* Constant Q: remove precalculated values again, I reckon they're not
  proving such a good tradeoff.

/* -*- c-basic-offset: 4 indent-tabs-mode: nil -*-  vi:set ts=8 sts=4 sw=4: */

/*
    QM DSP Library

    Centre for Digital Music, Queen Mary, University of London.
    This file copyright 2005 Nicolas Chetry, copyright 2008 QMUL.
    All rights reserved.
*/

#ifndef MFCC_H
#define MFCC_H

#include "base/Window.h"

class FFTReal;

struct MFCCConfig {
    int FS;
    int fftsize;
    int nceps;
    double logpower;
    bool want_c0;
    WindowType window;
    MFCCConfig(int _FS) :
        FS(_FS), fftsize(2048), nceps(19),
        logpower(1.0), want_c0(true), window(HammingWindow) { }
};

class MFCC
{
public:
    MFCC(MFCCConfig config);
    virtual ~MFCC();

    /**
     * Process time-domain input data.  inframe must contain
     * getfftlength() samples.  outceps must contain space for nceps
     * values, plus one if want_c0 is specified.
     */
    int process(const double *inframe, double *outceps);

    /**
     * Process time-domain input data.  real and imag must contain
     * getfftlength()/2+1 elements (i.e. the conjugate half of the FFT
     * is not expected).  outceps must contain space for nceps values,
     * plus one if want_c0 is specified.
     */
    int process(const double *real, const double *imag, double *outceps);

    int getfftlength() const { return fftSize; }

private:
    /* Filter bank parameters */
    double  lowestFrequency; 
    int     linearFilters; 
    double  linearSpacing;
    int     logFilters;
    double  logSpacing;
    
    /* FFT length */
    int     fftSize;
    
    int     totalFilters;
    double  logPower;
    
    /* Misc. */
    int     samplingRate;
    int     nceps;
    
    /* MFCC vector */
    double  *ceps;
    
    double  **mfccDCTMatrix;
    double  **mfccFilterWeights;
    
    /* The analysis window */
    Window<double> *window;
    
    /* For the FFT */
    double *realOut;
    double *imagOut;
    double *fftMag;
    double *earMag;
    FFTReal *fft;

    /* Set if user want C0 */
    int WANT_C0;
};


#endif