transform_sliding_window_cmn {torchaudio} | R Documentation |
sliding-window Cepstral Mean Normalization
Description
Apply sliding-window cepstral mean (and optionally variance) normalization per utterance.
Usage
transform_sliding_window_cmn(
cmn_window = 600,
min_cmn_window = 100,
center = FALSE,
norm_vars = FALSE
)
Arguments
cmn_window |
(int, optional): Window in frames for running average CMN computation (int, default = 600) |
min_cmn_window |
(int, optional): Minimum CMN window used at start of decoding (adds latency only at start).
Only applicable if center == |
center |
(bool, optional): If |
norm_vars |
(bool, optional): If |
Details
forward param: waveform (Tensor): Tensor of audio of dimension (..., time).
Value
Tensor: Tensor of audio of dimension (..., time).
[Package torchaudio version 0.3.1 Index]