MockingBird/vocoder/fregan/stft_loss.py

136 lines
4.8 KiB
Python
Raw Normal View History

# -*- coding: utf-8 -*-
# Copyright 2019 Tomoki Hayashi
# MIT License (https://opensource.org/licenses/MIT)
"""STFT-based Loss modules."""
import torch
import torch.nn.functional as F
def stft(x, fft_size, hop_size, win_length, window):
"""Perform STFT and convert to magnitude spectrogram.
Args:
x (Tensor): Input signal tensor (B, T).
fft_size (int): FFT size.
hop_size (int): Hop size.
win_length (int): Window length.
window (str): Window function type.
Returns:
Tensor: Magnitude spectrogram (B, #frames, fft_size // 2 + 1).
"""
x_stft = torch.stft(x, fft_size, hop_size, win_length, window)
real = x_stft[..., 0]
imag = x_stft[..., 1]
# NOTE(kan-bayashi): clamp is needed to avoid nan or inf
return torch.sqrt(torch.clamp(real ** 2 + imag ** 2, min=1e-7)).transpose(2, 1)
class SpectralConvergengeLoss(torch.nn.Module):
"""Spectral convergence loss module."""
def __init__(self):
"""Initilize spectral convergence loss module."""
super(SpectralConvergengeLoss, self).__init__()
def forward(self, x_mag, y_mag):
"""Calculate forward propagation.
Args:
x_mag (Tensor): Magnitude spectrogram of predicted signal (B, #frames, #freq_bins).
y_mag (Tensor): Magnitude spectrogram of groundtruth signal (B, #frames, #freq_bins).
Returns:
Tensor: Spectral convergence loss value.
"""
return torch.norm(y_mag - x_mag, p="fro") / torch.norm(y_mag, p="fro")
class LogSTFTMagnitudeLoss(torch.nn.Module):
"""Log STFT magnitude loss module."""
def __init__(self):
"""Initilize los STFT magnitude loss module."""
super(LogSTFTMagnitudeLoss, self).__init__()
def forward(self, x_mag, y_mag):
"""Calculate forward propagation.
Args:
x_mag (Tensor): Magnitude spectrogram of predicted signal (B, #frames, #freq_bins).
y_mag (Tensor): Magnitude spectrogram of groundtruth signal (B, #frames, #freq_bins).
Returns:
Tensor: Log STFT magnitude loss value.
"""
return F.l1_loss(torch.log(y_mag), torch.log(x_mag))
class STFTLoss(torch.nn.Module):
"""STFT loss module."""
def __init__(self, fft_size=1024, shift_size=120, win_length=600, window="hann_window"):
"""Initialize STFT loss module."""
super(STFTLoss, self).__init__()
self.fft_size = fft_size
self.shift_size = shift_size
self.win_length = win_length
self.window = getattr(torch, window)(win_length)
self.spectral_convergenge_loss = SpectralConvergengeLoss()
self.log_stft_magnitude_loss = LogSTFTMagnitudeLoss()
def forward(self, x, y):
"""Calculate forward propagation.
Args:
x (Tensor): Predicted signal (B, T).
y (Tensor): Groundtruth signal (B, T).
Returns:
Tensor: Spectral convergence loss value.
Tensor: Log STFT magnitude loss value.
"""
x_mag = stft(x, self.fft_size, self.shift_size, self.win_length, self.window.to(x.get_device()))
y_mag = stft(y, self.fft_size, self.shift_size, self.win_length, self.window.to(x.get_device()))
sc_loss = self.spectral_convergenge_loss(x_mag, y_mag)
mag_loss = self.log_stft_magnitude_loss(x_mag, y_mag)
return sc_loss, mag_loss
class MultiResolutionSTFTLoss(torch.nn.Module):
"""Multi resolution STFT loss module."""
def __init__(self,
fft_sizes=[1024, 2048, 512],
hop_sizes=[120, 240, 50],
win_lengths=[600, 1200, 240],
window="hann_window"):
"""Initialize Multi resolution STFT loss module.
Args:
fft_sizes (list): List of FFT sizes.
hop_sizes (list): List of hop sizes.
win_lengths (list): List of window lengths.
window (str): Window function type.
"""
super(MultiResolutionSTFTLoss, self).__init__()
assert len(fft_sizes) == len(hop_sizes) == len(win_lengths)
self.stft_losses = torch.nn.ModuleList()
for fs, ss, wl in zip(fft_sizes, hop_sizes, win_lengths):
self.stft_losses += [STFTLoss(fs, ss, wl, window)]
def forward(self, x, y):
"""Calculate forward propagation.
Args:
x (Tensor): Predicted signal (B, T).
y (Tensor): Groundtruth signal (B, T).
Returns:
Tensor: Multi resolution spectral convergence loss value.
Tensor: Multi resolution log STFT magnitude loss value.
"""
sc_loss = 0.0
mag_loss = 0.0
for f in self.stft_losses:
sc_l, mag_l = f(x, y)
sc_loss += sc_l
mag_loss += mag_l
sc_loss /= len(self.stft_losses)
mag_loss /= len(self.stft_losses)
return sc_loss, mag_loss