aeon performs a series of customizable transformations on the audio before provisioning the data to the model.
- Probabilistically add noise to raw audio waveform (with the probability controlled by the
add_noise_probabilityparameter). Noise is chosen from a random file in
noise_index_fileand added at a random offset and scaling (controlled by the
noise_levelparameter). Noise addition happens only in the time domain (as opposed to the spectral domain).
time_scale_fractionhas been set to a pair of values
(tmin, tmax), then the spectral frames will be randomly squeezed or stretched in the time domain according to a random value chosen uniformly from the interval between
tmax. For example:
|noise_index_file (string)||File of pathnames to noisy audio files, one per line.|
|noise_level (tuple(float, float))||(0.0, 0.5)||How much noise to add (a value of 1 would be 0 dB SNR). Each clip applies its own value chosen randomly from with the given bounds.|
|add_noise_probability (float)||0.0||Probability of adding noise|
|time_scale_fraction (tuple(float, float))||(1.0, 1.0)||Scale factor for simple linear time-warping. Each clip applies its own value chosen randomly from with the given bounds.|