speechaugs 0.0.4

Waveform augmentations

speechaugs

Single-channel waveforms augmentations for speech recognition models.

---

Augmentations:

• Time Stretch
• Forward Time Shift
• Pitch Shift
• Colored Noise (white, pink, brown, blue, violet, grey)
• Zero Samples
• Clipping samples
• Inversion

---

Colab Example You can see examples of all augmentations and listen to resulting audios on this page with Colab notebook.

---

Installation

pip install speechaugs

---

Time Stretch

Stretch a wavefom in time with randomly chosen rate. Is implemented using librosa.effects.time_stretch.

Forward Time Shift

Shift a waveform forwards in time.

Pitch Shift

Shift a pitch by n_steps semitones. Is implemented using librosa.effects.pitch_shift.

The work of PitchShift can be better illustrated on the MelSpectrograms of waveforms.

Higher pitch (+9 semitones):

Lower pitch (-5 semitones)

Colored Noise

Add noise of different color to a waveform. Color of noise depends on the spectral density of the noise. You can go to wiki page for more information.

This class is implemented using colorednoise package. The color of noise is randomly choosen.

White Noise

Brown Noise

Zero Samples

Set some percentage of samples to zero.

Clipping Samples

Clip some percentage of samples from a waveform.

Inversion

Change sign of waveform samples.

---

Usage example (with default parameters)

Import:

from speechaugs import TimeStretchLibrosa, ForwardTimeShift, PitchShiftLibrosa, ColoredNoise, Inversion, ZeroSamples, ClippingSamples

Other libs:

import torch, torchaudio
import albumentations as A

Usage:

ex_waveform, sr = torchaudio.load('audio_filename')

transforms = A.Compose([
    ForwardTimeShift(p=0.5),
    Inversion(p=0.5),
    A.OneOf([ZeroSamples(p=0.5), ClippingSamples(p=0.5)], p=0.5),
    A.OneOf([TimeStretchLibrosa(p=0.5), PitchShiftLibrosa(p=0.5)], p = 0.5),
    ColoredNoise(p=0.5)
], p=1.0)

augmented = transforms(waveform=ex_waveform)['waveform']