utils.py 文件源码

def ispecgram(spec,
              n_fft=512,
              hop_length=None,
              mask=True,
              log_mag=True,
              re_im=False,
              dphase=True,
              mag_only=True,
              num_iters=1000):
  """Inverse Spectrogram using librosa.

  Args:
    spec: 3-D specgram array [freqs, time, (mag_db, dphase)].
    n_fft: Size of the FFT.
    hop_length: Stride of FFT. Defaults to n_fft/2.
    mask: Reverse the mask of the phase derivative by the magnitude.
    log_mag: Use the logamplitude.
    re_im: Output Real and Imag. instead of logMag and dPhase.
    dphase: Use derivative of phase instead of phase.
    mag_only: Specgram contains no phase.
    num_iters: Number of griffin-lim iterations for mag_only.

  Returns:
    audio: 1-D array of sound samples. Peak normalized to 1.
  """
  if not hop_length:
    hop_length = n_fft // 2

  ifft_config = dict(win_length=n_fft, hop_length=hop_length, center=True)

  if mag_only:
    mag = spec[:, :, 0]
    phase_angle = np.pi * np.random.rand(*mag.shape)
  elif re_im:
    spec_real = spec[:, :, 0] + 1.j * spec[:, :, 1]
  else:
    mag, p = spec[:, :, 0], spec[:, :, 1]
    if mask and log_mag:
      p /= (mag + 1e-13 * np.random.randn(*mag.shape))
    if dphase:
      # Roll up phase
      phase_angle = np.cumsum(p * np.pi, axis=1)
    else:
      phase_angle = p * np.pi

  # Magnitudes
  if log_mag:
    mag = (mag - 1.0) * 120.0
    mag = 10**(mag / 20.0)
  phase = np.cos(phase_angle) + 1.j * np.sin(phase_angle)
  spec_real = mag * phase

  if mag_only:
    audio = griffin_lim(
        mag, phase_angle, n_fft, hop_length, num_iters=num_iters)
  else:
    audio = librosa.core.istft(spec_real, **ifft_config)
  return np.squeeze(audio / audio.max())