annotate dsp/tempotracking/TempoTrackV2.h @ 298:255e431ae3d4

* 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 2008-2009 Matthew Davies and QMUL.
    All rights reserved.
*/


#ifndef TEMPOTRACKV2_H
#define TEMPOTRACKV2_H

#include <vector>

using std::vector;

//!!! Question: how far is this actually sample rate dependent?  I
// think it does produce plausible results for e.g. 48000 as well as
// 44100, but surely the fixed window sizes and comb filtering will
// make it prefer double or half time when run at e.g. 96000?

class TempoTrackV2  
{
public:
    /**
     * Construct a tempo tracker that will operate on beat detection
     * function data calculated from audio at the given sample rate
     * with the given frame increment.
     *
     * Currently the sample rate and increment are used only for the
     * conversion from beat frame location to bpm in the tempo array.
     */
    TempoTrackV2(float sampleRate, size_t dfIncrement);
    ~TempoTrackV2();

    // Returned beat periods are given in df increment units; tempi in bpm
    void calculateBeatPeriod(const vector<double> &df,
                             vector<double> &beatPeriod,
                             vector<double> &tempi);

    // Returned beat positions are given in df increment units
    void calculateBeats(const vector<double> &df,
                        const vector<double> &beatPeriod,
                        vector<double> &beats);

private:
    typedef vector<int> i_vec_t;
    typedef vector<vector<int> > i_mat_t;
    typedef vector<double> d_vec_t;
    typedef vector<vector<double> > d_mat_t;

    float m_rate;
    size_t m_increment;

    void adapt_thresh(d_vec_t &df);
    double mean_array(const d_vec_t &dfin, int start, int end);
    void filter_df(d_vec_t &df);
    void get_rcf(const d_vec_t &dfframe, const d_vec_t &wv, d_vec_t &rcf);
    void viterbi_decode(const d_mat_t &rcfmat, const d_vec_t &wv,
                        d_vec_t &bp, d_vec_t &tempi);
    double get_max_val(const d_vec_t &df);
    int get_max_ind(const d_vec_t &df);
    void normalise_vec(d_vec_t &df);
};

#endif