#
# Copyright (C) 2016-2019 by Nathan Lovato, Daniel Oakey, Razvan Radulescu, and contributors
#
# This file is part of Power Sequencer.
#
# Power Sequencer is free software: you can redistribute it and/or modify it under the terms of the
# GNU General Public License as published by the Free Software Foundation, either version 3 of the
# License, or (at your option) any later version.
#
# Power Sequencer is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY;
# without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License along with Power Sequencer. If
# not, see <https://www.gnu.org/licenses/>.
#
import numpy as np

from scipy.signal import hamming, lfilter
from scipy.fftpack import fft
from scipy.fftpack.realtransforms import dct

from .trfbank import trfbank
from .segment_axis import segment_axis


def mfcc(input, nwin=256, nfft=512, fs=16000, nceps=13):
    """Compute Mel Frequency Cepstral Coefficients.

    Parameters
    ----------
    input: ndarray
        input from which the coefficients are computed

    Returns
    -------
    ceps: ndarray
        Mel-cepstrum coefficients
    mspec: ndarray
        Log-spectrum in the mel-domain.

    Notes
    -----
    MFCC are computed as follows:
        * Pre-processing in time-domain (pre-emphasizing)
        * Compute the spectrum amplitude by windowing with a Hamming window
        * Filter the signal in the spectral domain with a triangular
        filter-bank, whose filters are approximatively linearly spaced on the
        mel scale, and have equal bandwidth in the mel scale
        * Compute the DCT of the log-spectrum

    References
    ----------
    .. [1] S.B. Davis and P. Mermelstein, "Comparison of parametric
           representations for monosyllabic word recognition in continuously
           spoken sentences", IEEE Trans. Acoustics. Speech, Signal Proc.
           ASSP-28 (4): 357-366, August 1980."""

    # MFCC parameters: taken from auditory toolbox
    over = nwin - 160
    # Pre-emphasis factor (to take into account the -6dB/octave rolloff of the
    # radiation at the lips level)
    prefac = 0.97

    # lowfreq = 400 / 3.
    lowfreq = 133.33
    # highfreq = 6855.4976
    linsc = 200 / 3.0
    logsc = 1.0711703

    nlinfil = 13
    nlogfil = 27
    nfil = nlinfil + nlogfil

    w = hamming(nwin, sym=0)

    fbank = trfbank(fs, nfft, lowfreq, linsc, logsc, nlinfil, nlogfil)[0]

    # ------------------
    # Compute the MFCC
    # ------------------
    extract = lfilter([1.0, -prefac], 1, input)
    framed = segment_axis(extract, nwin, over) * w

    # Compute the spectrum magnitude
    spec = np.abs(fft(framed, nfft, axis=-1))
    # Filter the spectrum through the triangle filterbank
    mspec = np.log10(np.dot(spec, fbank.T))
    # Use the DCT to 'compress' the coefficients (spectrum -> cepstrum domain)
    ceps = dct(mspec, type=2, norm="ortho", axis=-1)[:, :nceps]

    return ceps, mspec, spec