DeepLearningExamples/PyTorch/SpeechSynthesis/HiFiGAN/common/audio_processing.py

# *****************************************************************************
#  Copyright (c) 2018, NVIDIA CORPORATION.  All rights reserved.
#
#  Redistribution and use in source and binary forms, with or without
#  modification, are permitted provided that the following conditions are met:
#      * Redistributions of source code must retain the above copyright
#        notice, this list of conditions and the following disclaimer.
#      * Redistributions in binary form must reproduce the above copyright
#        notice, this list of conditions and the following disclaimer in the
#        documentation and/or other materials provided with the distribution.
#      * Neither the name of the NVIDIA CORPORATION nor the
#        names of its contributors may be used to endorse or promote products
#        derived from this software without specific prior written permission.
#
#  THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
#  ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
#  WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
#  DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE FOR ANY
#  DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
#  (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
#  LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
#  ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
#  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
#  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
#
# *****************************************************************************

import librosa.util as librosa_util
import numpy as np
import torch
from scipy.signal import get_window


def window_sumsquare(window, n_frames, hop_length=200, win_length=800,
                     n_fft=800, dtype=np.float32, norm=None):
    """
    # from librosa 0.6
    Compute the sum-square envelope of a window function at a given hop length.

    This is used to estimate modulation effects induced by windowing
    observations in short-time fourier transforms.

    Parameters
    ----------
    window : string, tuple, number, callable, or list-like
        Window specification, as in `get_window`

    n_frames : int > 0
        The number of analysis frames

    hop_length : int > 0
        The number of samples to advance between frames

    win_length : [optional]
        The length of the window function.  By default, this matches `n_fft`.

    n_fft : int > 0
        The length of each analysis frame.

    dtype : np.dtype
        The data type of the output

    Returns
    -------
    wss : np.ndarray, shape=`(n_fft + hop_length * (n_frames - 1))`
        The sum-squared envelope of the window function
    """
    if win_length is None:
        win_length = n_fft

    n = n_fft + hop_length * (n_frames - 1)
    x = np.zeros(n, dtype=dtype)

    # Compute the squared window at the desired length
    win_sq = get_window(window, win_length, fftbins=True)
    win_sq = librosa_util.normalize(win_sq, norm=norm)**2
    win_sq = librosa_util.pad_center(win_sq, size=n_fft)

    # Fill the envelope
    for i in range(n_frames):
        sample = i * hop_length
        x[sample:min(n, sample + n_fft)] += win_sq[:max(0, min(n_fft, n - sample))]
    return x


def griffin_lim(magnitudes, stft_fn, n_iters=30):
    """
    PARAMS
    ------
    magnitudes: spectrogram magnitudes
    stft_fn: STFT class with transform (STFT) and inverse (ISTFT) methods
    """

    angles = np.angle(np.exp(2j * np.pi * np.random.rand(*magnitudes.size())))
    angles = angles.astype(np.float32)
    angles = torch.autograd.Variable(torch.from_numpy(angles))
    signal = stft_fn.inverse(magnitudes, angles).squeeze(1)

    for i in range(n_iters):
        _, angles = stft_fn.transform(signal)
        signal = stft_fn.inverse(magnitudes, angles).squeeze(1)
    return signal


def dynamic_range_compression(x, C=1, clip_val=1e-5):
    """
    PARAMS
    ------
    C: compression factor
    """
    return torch.log(torch.clamp(x, min=clip_val) * C)


def dynamic_range_decompression(x, C=1):
    """
    PARAMS
    ------
    C: compression factor used to compress
    """
    return torch.exp(x) / C