Source code for espnet2.gan_svs.uhifigan.sine_generator

import numpy as np
import torch


[docs]class SineGen(torch.nn.Module): """Definition of sine generator SineGen(samp_rate, harmonic_num = 0, sine_amp = 0.1, noise_std = 0.003, voiced_threshold = 0, flag_for_pulse=False) sample_rate: sampling rate in Hz harmonic_num: number of harmonic overtones (default 0) sine_amp: amplitude of sine-wavefrom (default 0.1) noise_std: std of Gaussian noise (default 0.003) voiced_thoreshold: F0 threshold for U/V classification (default 0) flag_for_pulse: this SinGen is used inside PulseGen (default False) Note: when flag_for_pulse is True, the first time step of a voiced segment is always sin(np.pi) or cos(0) """ def __init__( self, sample_rate, harmonic_num=0, sine_amp=0.1, noise_std=0.003, voiced_threshold=0, flag_for_pulse=False, ): super(SineGen, self).__init__() self.sine_amp = sine_amp self.noise_std = noise_std self.harmonic_num = harmonic_num self.dim = self.harmonic_num + 1 self.sampling_rate = sample_rate self.voiced_threshold = voiced_threshold self.flag_for_pulse = flag_for_pulse def _f02uv(self, f0): # generate uv signal uv = torch.ones_like(f0) uv = uv * (f0 > self.voiced_threshold) return uv def _f02sine(self, f0_values): """f0_values: (batchsize, length, dim) where dim indicates fundamental tone and overtones """ # convert to F0 in rad. The interger part n can be ignored # because 2 * np.pi * n doesn't affect phase rad_values = (f0_values / self.sampling_rate) % 1 # initial phase noise (no noise for fundamental component) rand_ini = torch.rand( f0_values.shape[0], f0_values.shape[2], device=f0_values.device ) rand_ini[:, 0] = 0 rad_values[:, 0, :] = rad_values[:, 0, :] + rand_ini # instantanouse phase sine[t] = sin(2*pi \sum_i=1 ^{t} rad) if not self.flag_for_pulse: # for normal case # To prevent torch.cumsum numerical overflow, # it is necessary to add -1 whenever \sum_k=1^n rad_value_k > 1. # Buffer tmp_over_one_idx indicates the time step to add -1. # This will not change F0 of sine because (x-1) * 2*pi = x *2*pi tmp_over_one = torch.cumsum(rad_values, 1) % 1 tmp_over_one_idx = (tmp_over_one[:, 1:, :] - tmp_over_one[:, :-1, :]) < 0 cumsum_shift = torch.zeros_like(rad_values) cumsum_shift[:, 1:, :] = tmp_over_one_idx * -1.0 sines = torch.sin( torch.cumsum(rad_values + cumsum_shift, dim=1) * 2 * np.pi ) else: # If necessary, make sure that the first time step of every # voiced segments is sin(pi) or cos(0) # This is used for pulse-train generation # identify the last time step in unvoiced segments uv = self._f02uv(f0_values) uv_1 = torch.roll(uv, shifts=-1, dims=1) uv_1[:, -1, :] = 1 u_loc = (uv < 1) * (uv_1 > 0) # get the instantanouse phase tmp_cumsum = torch.cumsum(rad_values, dim=1) # different batch needs to be processed differently for idx in range(f0_values.shape[0]): temp_sum = tmp_cumsum[idx, u_loc[idx, :, 0], :] temp_sum[1:, :] = temp_sum[1:, :] - temp_sum[0:-1, :] # stores the accumulation of i.phase within # each voiced segments tmp_cumsum[idx, :, :] = 0 tmp_cumsum[idx, u_loc[idx, :, 0], :] = temp_sum # rad_values - tmp_cumsum: remove the accumulation of i.phase # within the previous voiced segment. i_phase = torch.cumsum(rad_values - tmp_cumsum, dim=1) # get the sines sines = torch.cos(i_phase * 2 * np.pi) return sines
[docs] def forward(self, f0): """sine_tensor, uv = forward(f0) input F0: tensor(batchsize=1, length, dim=1) f0 for unvoiced steps should be 0 output sine_tensor: tensor(batchsize=1, length, dim) output uv: tensor(batchsize=1, length, 1) """ with torch.no_grad(): f0_buf = torch.zeros(f0.shape[0], f0.shape[1], self.dim, device=f0.device) # print("f0_buf", f0_buf.shape) # print("f0", f0.shape) # fundamental component f0_buf[:, :, 0] = f0[:, :, 0] for idx in np.arange(self.harmonic_num): # idx + 2: the (idx+1)-th overtone, (idx+2)-th harmonic f0_buf[:, :, idx + 1] = f0_buf[:, :, 0] * (idx + 2) # generate sine waveforms sine_waves = self._f02sine(f0_buf) * self.sine_amp # generate uv signal # uv = torch.ones(f0.shape) # uv = uv * (f0 > self.voiced_threshold) uv = self._f02uv(f0) # noise: for unvoiced should be similar to sine_amp # std = self.sine_amp/3 -> max value ~ self.sine_amp # . for voiced regions is self.noise_std noise_amp = uv * self.noise_std + (1 - uv) * self.sine_amp / 3 noise = noise_amp * torch.randn_like(sine_waves) # first: set the unvoiced part to 0 by uv # then: additive noise sine_waves = sine_waves * uv + noise return sine_waves, uv, noise