functional_dither {torchaudio} | R Documentation |
Dither (functional)
Description
Dither increases the perceived dynamic range of audio stored at a particular bit-depth by eliminating nonlinear truncation distortion (i.e. adding minimally perceived noise to mask distortion caused by quantization).
Usage
functional_dither(waveform, density_function = "TPDF", noise_shaping = FALSE)
Arguments
waveform |
(Tensor): Tensor of audio of dimension (..., time) |
density_function |
(str, optional): The density function of a continuous random variable (Default: |
noise_shaping |
(bool, optional): a filtering process that shapes the spectral
energy of quantisation error (Default: |
Value
tensor
: waveform dithered
[Package torchaudio version 0.3.1 Index]