kaldi_resample_waveform: Kaldi's Resample Waveform

In torchaudio: R Interface to 'pytorch''s 'torchaudio'

Kaldi's Resample Waveform

Description

Resamples the waveform at the new frequency.

Usage

kaldi_resample_waveform(
  waveform,
  orig_freq,
  new_freq,
  lowpass_filter_width = 6
)

Arguments

waveform	(Tensor): The input signal of size (c, n)
orig_freq	(float): The original frequency of the signal
new_freq	(float): The desired frequency
lowpass_filter_width	(int, optional): Controls the sharpness of the filter, more == sharper but less efficient. We suggest around 4 to 10 for normal use. (Default: 6)

Details

This matches Kaldi's OfflineFeatureTpl ResampleWaveform which uses a LinearResample (resample a signal at linearly spaced intervals to upsample/downsample a signal). LinearResample (LR) means that the output signal is at linearly spaced intervals (i.e the output signal has a frequency of new_freq). It uses sinc/bandlimited interpolation to upsample/downsample the signal.

Value

Tensor: The waveform at the new frequency

References

• https://ccrma.stanford.edu/~jos/resample/Theory_Ideal_Bandlimited_Interpolation.html

• https://github.com/kaldi-asr/kaldi/blob/master/src/feat/resample.h#L56

torchaudio documentation built on Feb. 16, 2023, 9:41 p.m.