A Python library for audio data augmentation. Inspired by albumentations. Useful for deep learning. Runs on CPU. Supports mono audio and partially multichannel audio. Can be integrated in training pipelines in e.g. Tensorflow/Keras or Pytorch. Has helped people get world-class results in Kaggle competitions. Is used by companies making next-generation audio products.
Need a Pytorch alternative with GPU support? Check out torch-audiomentations!
pip install audiomentations
Some features have extra dependencies. Extra python package dependencies can be installed by running
pip install audiomentations[extras]
| Feature | Extra dependencies |
|---|---|
| Load 24-bit wav files fast | wavio |
LoudnessNormalization |
pyloudnorm |
Mp3Compression |
ffmpeg and [pydub or lameenc] |
Note: ffmpeg can be installed via e.g. conda or from the official ffmpeg download page.
from audiomentations import Compose, AddGaussianNoise, TimeStretch, PitchShift, Shift
import numpy as np
SAMPLE_RATE = 16000
augment = Compose([
AddGaussianNoise(min_amplitude=0.001, max_amplitude=0.015, p=0.5),
TimeStretch(min_rate=0.8, max_rate=1.25, p=0.5),
PitchShift(min_semitones=-4, max_semitones=4, p=0.5),
Shift(min_fraction=-0.5, max_fraction=0.5, p=0.5),
])
# Generate 2 seconds of dummy audio for the sake of example
samples = np.random.uniform(low=-0.2, high=0.2, size=(32000,)).astype(np.float32)
# Augment/transform/perturb the audio data
augmented_samples = augment(samples=samples, sample_rate=SAMPLE_RATE)Go to audiomentations/augmentations/transforms.py to see the waveform transforms you can apply, and what arguments they have.
See audiomentations/augmentations/spectrogram_transforms.py for spectrogram transforms.
Added in v0.9.0
Mix in another sound, e.g. a background noise. Useful if your original sound is clean and you want to simulate an environment where background noise is present.
Can also be used for mixup, as in https://arxiv.org/pdf/1710.09412.pdf
A folder of (background noise) sounds to be mixed in must be specified. These sounds should ideally be at least as long as the input sounds to be transformed. Otherwise, the background sound will be repeated, which may sound unnatural.
Note that the gain of the added noise is relative to the amount of signal in the input. This implies that if the input is completely silent, no noise will be added.
Added in v0.1.0
Add gaussian noise to the samples
Added in v0.7.0
Add gaussian noise to the samples with random Signal to Noise Ratio (SNR)
Added in v0.7.0
Convolve the audio with a random impulse response. Impulse responses can be created using e.g. http://tulrich.com/recording/ir_capture/
Some datasets of impulse responses are publicly available:
- EchoThief containing 115 impulse responses acquired in a wide range of locations.
- The MIT McDermott dataset containing 271 impulse responses acquired in everyday places.
Impulse responses are represented as wav files in the given ir_path.
Added in v0.9.0
Mix in various (bursts of overlapping) sounds with random pauses between. Useful if your original sound is clean and you want to simulate an environment where short noises sometimes occur.
A folder of (noise) sounds to be mixed in must be specified.
Added in v0.8.0
Distort signal by clipping a random percentage of points
The percentage of points that will be clipped is drawn from a uniform distribution between the two input parameters min_percentile_threshold and max_percentile_threshold. If for instance 30% is drawn, the samples are clipped if they're below the 15th or above the 85th percentile.
Added in v0.7.0
Mask some frequency band on the spectrogram. Inspired by https://arxiv.org/pdf/1904.08779.pdf
Added in v0.11.0
Multiply the audio by a random amplitude factor to reduce or increase the volume. This technique can help a model become somewhat invariant to the overall gain of the input audio.
Warning: This transform can return samples outside the [-1, 1] range, which may lead to clipping or wrap distortion, depending on what you do with the audio in a later stage. See also https://en.wikipedia.org/wiki/Clipping_(audio)#Digital_clipping
Added in v0.12.0
Compress the audio using an MP3 encoder to lower the audio quality. This may help machine learning models deal with compressed, low-quality audio.
This transform depends on either lameenc or pydub/ffmpeg.
Note that bitrates below 32 kbps are only supported for low sample rates (up to 24000 hz).
Note: When using the lameenc backend, the output may be slightly longer than the input due to the fact that the LAME encoder inserts some silence at the beginning of the audio.
Added in v0.14.0
Apply a constant amount of gain to match a specific loudness. This is an implementation of ITU-R BS.1770-4.
Warning: This transform can return samples outside the [-1, 1] range, which may lead to clipping or wrap distortion, depending on what you do with the audio in a later stage. See also https://en.wikipedia.org/wiki/Clipping_(audio)#Digital_clipping
Added in v0.6.0
Apply a constant amount of gain, so that highest signal level present in the sound becomes 0 dBFS, i.e. the loudest level allowed if all samples must be between -1 and 1. Also known as peak normalization.
Added in v0.4.0
Pitch shift the sound up or down without changing the tempo
Added in v0.11.0
Flip the audio samples upside-down, reversing their polarity. In other words, multiply the waveform by -1, so negative values become positive, and vice versa. The result will sound the same compared to the original when played back in isolation. However, when mixed with other audio sources, the result may be different. This waveform inversion technique is sometimes used for audio cancellation or obtaining the difference between two waveforms. However, in the context of audio data augmentation, this transform can be useful when training phase-aware machine learning models.
Added in v0.8.0
Resample signal using librosa.core.resample
To do downsampling only set both minimum and maximum sampling rate lower than original sampling rate and vice versa to do upsampling only.
Added in v0.5.0
Shift the samples forwards or backwards, with or without rollover
Added in v0.7.0
Make a randomly chosen part of the audio silent. Inspired by https://arxiv.org/pdf/1904.08779.pdf
Added in v0.2.0
Time stretch the signal without changing the pitch
Added in v0.7.0
Trim leading and trailing silence from an audio signal using librosa.effects.trim
Added in v0.13.0
Shuffle the channels of a multichannel spectrogram. This can help combat positional bias.
Added in v0.13.0
Mask a set of frequencies in a spectrogram, à la Google AI SpecAugment. This type of data augmentation has proved to make speech recognition models more robust.
The masked frequencies can be replaced with either the mean of the original values or a given constant (e.g. zero).
- Some transforms do not support multichannel audio yet. See Multichannel audio
- Expects the input dtype to be float32, and have values between -1 and 1.
- The code runs on CPU, not GPU. For a GPU-compatible version, check out pytorch-audiomentations
- Multiprocessing is not officially supported yet. See also #46
- Not compatible with scipy>=1.6 due to the way 24-bit and 32-bit int wav files are loaded
Contributions are welcome!
Most transforms, but not all, support 2D numpy arrays with shapes like (num_channels, num_samples)
The following table is valid for v0.14.0 - v0.16.0 only
| Transform | Supports multichannel audio? |
|---|---|
| AddBackgroundNoise | No, 1D only |
| AddGaussianNoise | Yes |
| AddGaussianSNR | Yes |
| AddImpulseResponse | No, 1D only |
| AddShortNoises | No, 1D only |
| ClippingDistortion | Yes |
| FrequencyMask | Yes |
| Gain | Yes |
| LoudnessNormalization | Yes, up to 5 channels |
| Mp3Compression | No, 1D only |
| Normalize | Yes |
| PitchShift | Yes |
| PolarityInversion | Yes |
| Resample | No, 1D only |
| Shift | Yes |
| SpecChannelShuffle | Yes |
| SpecFrequencyMask | Yes |
| TimeMask | Yes |
| TimeStretch | Yes |
| Trim | No, 1D only |
- Add a
fadeoption inShiftfor eliminating unwanted clicks - Add support for 32-bit int wav loading with scipy>=1.6
- Avoid division by zero in
AddImpulseResponsewhen input is digital silence (all zeros)
- Implement
SpecComposefor applying a pipeline of spectrogram transforms. Thanks to omerferhatt. - Fix a bug in
SpecChannelShufflewhere it did not support more than 3 audio channels. Thanks to omerferhatt. - Limit scipy version range to >=1.0,<1.6 to avoid issues with loading 24-bit wav files. Support for scipy>=1.6 will be added later.
- Fix picklability of instances of
AddImpulseResponse,AddBackgroundNoiseandAddShortNoises - Add an option
leave_length_unchangedtoAddImpulseResponse
- Implement
LoudnessNormalization - Implement
randomize_parametersinCompose. Thanks to SolomidHero. - Add multichannel support to
AddGaussianNoise,AddGaussianSNR,ClippingDistortion,FrequencyMask,PitchShift,Shift,TimeMaskandTimeStretch
- Show a warning if a waveform had to be resampled after loading it. This is because resampling is slow. Ideally, files on disk should already have the desired sample rate.
- Correctly find audio files with upper case filename extensions.
- Lay the foundation for spectrogram transforms. Implement
SpecChannelShuffleandSpecFrequencyMask. - Fix a bug where AddBackgroundNoise crashed when trying to add digital silence to an input. Thanks to juheeuu.
- Configurable LRU cache for transforms that use external sound files. Thanks to alumae.
- Officially add multichannel support to
Normalize
- Speed up
AddBackgroundNoise,AddShortNoisesandAddImpulseResponseby loading wav files with scipy or wavio instead of librosa.
- Implement
Mp3Compression - Python <= 3.5 is no longer officially supported, since Python 3.5 has reached end-of-life
- Expand range of supported
librosaversions - Officially support multichannel audio in
GainandPolarityInversion - Add m4a and opus to the list of recognized audio filename extensions
- Breaking change: Internal util functions are no longer exposed directly. If you were doing
e.g.
from audiomentations import calculate_rms, now you have to dofrom audiomentations.core.utils import calculate_rms
- Implement
GainandPolarityInversion. Thanks to Spijkervet for the inspiration.
- Improve the performance of
AddBackgroundNoiseandAddShortNoisesby optimizing the implementation ofcalculate_rms. - Improve compatibility of output files written by the demo script. Thanks to xwJohn.
- Fix division by zero bug in
Normalize. Thanks to ZFTurbo.
- Breaking change:
AddImpulseResponse,AddBackgroundNoiseandAddShortNoisesnow include subfolders when searching for files. This is useful when your sound files are organized in subfolders. AddImpulseResponse,AddBackgroundNoiseandAddShortNoisesnow support aiff files in addition to flac, mp3, ogg and wav- Fix filter instability bug in
FrequencyMask. Thanks to kvilouras.
- Disregard non-audio files when looking for impulse response files
- Remember randomized/chosen effect parameters. This allows for freezing the parameters and applying the same effect to multiple sounds. Use transform.freeze_parameters() and transform.unfreeze_parameters() for this.
- Fix a bug in
ClippingDistortionwhere the min_percentile_threshold was not respected as expected. - Implement transform.serialize_parameters(). Useful for when you want to store metadata on how a sound was perturbed.
- Switch to a faster convolve implementation. This makes
AddImpulseResponsesignificantly faster. - Add a rollover parameter to
Shift. This allows for introducing silence instead of a wrapped part of the sound. - Expand supported range of librosa versions
- Add support for flac in
AddImpulseResponse - Implement
AddBackgroundNoisetransform. Useful for when you want to add background noise to all of your sound. You need to give it a folder of background noises to choose from. - Implement
AddShortNoises. Useful for when you want to add (bursts of) short noise sounds to your input audio. - Improve handling of empty input
- Add shuffle parameter in
Composer - Add
Resampletransformation - Add
ClippingDistortiontransformation - Add
fadeparameter toTimeMask
Thanks to askskro
Add new transforms:
AddGaussianSNRAddImpulseResponseFrequencyMaskTimeMaskTrim
Thanks to karpnv
- Implement peak normalization
- Implement
Shifttransform - Ensure p is within bounds
- Implement
PitchShifttransform - Fix output dtype of
AddGaussianNoise
Implement leave_length_unchanged in TimeStretch
- Add
TimeStretchtransform - Parametrize
AddGaussianNoise
Initial release. Includes only one transform: AddGaussianNoise
Install the dependencies specified in requirements.txt
Format the code with black
pytest
python -m demo.demo
Audiomentations isn't the only python library that can do various types of audio data augmentation/degradation! Here's an overview:
| Name | Github stars | License | Last commit | GPU support? |
|---|---|---|---|---|
| audio-degradation-toolbox |  |
 |
 |
 |
| audio_degrader |  |
 |
 |
|
| audiomentations |  |
 |
 |
|
| kapre |  |
 |
 |
 |
| muda |  |
 |
 |
|
| nlpaug |  |
 |
 |
|
| pydiogment |  |
 |
 |
|
| python-audio-effects |  |
 |
 |
|
| sigment |  |
 |
 |
|
| SpecAugment |  |
 |
 |
 |
| spec_augment |  |
 |
 |
 |
| torch-audiomentations |  |
 |
 |
|
| WavAugment |  |
 |
 |
|
Thanks to Nomono for backing audiomentations.
Thanks to all contributors who help improving audiomentations.