Augmenter that apply mask normalization to audio.

class'max', zone=(0.2, 0.8), coverage=0.3, name='Normalize_Aug', verbose=0, stateless=True)[source]


  • method (str) – It supports ‘minmax’, ‘max’ and ‘standard’. For ‘minmax’, data will be substracted by min value in data and dividing by range of max value and min value. For ‘max’, data will be divided by max value only. For ‘standard’, data will be substracted by mean value and dividing by value of standard deviation. If ‘random’ is used, method will be picked randomly in each augment.
  • zone (tuple) – Assign a zone for augmentation. Default value is (0.2, 0.8) which means that no any augmentation will be applied in first 20% and last 20% of whole audio.
  • coverage (float) – Portion of augmentation. Value should be between 0 and 1. If 0.1 is assigned, augment operation will be applied to target audio segment. For example, the audio duration is 60 seconds while zone and coverage are (0.2, 0.8) and 0.7 respectively. 25.2 seconds ((0.8-0.2)*0.7*60) audio will be augmented.
  • name (str) – Name of this augmenter
>>> import as naa
>>> aug = naa.NormalizeAug()
augment(data, n=1, num_thread=1)
  • data (object/list) – Data for augmentation. It can be list of data (e.g. list of string or numpy) or single element (e.g. string or numpy). Numpy format only supports audio or spectrogram data. For text data, only support string or list of string.
  • n (int) – Default is 1. Number of unique augmented output. Will be force to 1 if input is list of data
  • num_thread (int) – Number of thread for data augmentation. Use this option when you are using CPU and n is larger than 1

Augmented data

>>> augmented_data = aug.augment(data)