Transform SpecAugment on the Mel Spectrogram

transform_spec_augment.py

  # ----------------------------
  # Augment the Spectrogram by masking out some sections of it in both the frequency
  # dimension (ie. horizontal bars) and the time dimension (vertical bars) to prevent
  # overfitting and to help the model generalise better. The masked sections are
  # replaced with the mean value.
  # ----------------------------
  @staticmethod
  def spectro_augment(spec, max_mask_pct=0.1, n_freq_masks=1, n_time_masks=1):
    _, n_mels, n_steps = spec.shape
    mask_value = spec.mean()
    aug_spec = spec

    freq_mask_param = max_mask_pct * n_mels
    for _ in range(n_freq_masks):
      aug_spec = transforms.FrequencyMasking(freq_mask_param)(aug_spec, mask_value)

    time_mask_param = max_mask_pct * n_steps
    for _ in range(n_time_masks):
      aug_spec = transforms.TimeMasking(time_mask_param)(aug_spec, mask_value)

    return aug_spec