Here is a way to quickly augment a folder of audio files:
cd ~
cd allie/features/audio_augmentation
python3 augment.py /Users/jimschwoebel/allie/load_dir
- augment_tsaug - adds noise and various shifts to audio files, addes 2x more data; see tutorial here.
- augment_addnoise - adds noise to an audio file.
- augment_noise - removes noise from audio files randomly.
- augment_pitch - shifts pitch up and down to correct for gender differences.
- augment_randomsplice - randomly splice an audio file to generate more data.
- augment_silence - add silence to an audio file to augment a dataset.
- augment_time - change time duration for a variety of audio files through making new files.
- augment_volume - change volume randomly (helps to mitigate effects of microphohne distance on a model).
| setting | description | default setting | all options |
|---|---|---|---|
| augment_data | whether or not to implement data augmentation policies during the model training process via default augmentation scripts. | True | True, False |
| default_audio_augmenters | the default augmentation strategies used during audio modeling if augment_data == True | ["augment_tsaug"] | ["augment_tsaug", "augment_addnoise", "augment_noise", "augment_pitch", "augment_randomsplice", "augment_silence", "augment_time", "augment_volume"] |