transform_mel_scale: Mel Scale

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

Mel Scale

Description

Turn a normal STFT into a mel frequency STFT, using a conversion matrix. This uses triangular filter banks.

Usage

transform_mel_scale(
  n_mels = 128,
  sample_rate = 16000,
  f_min = 0,
  f_max = NULL,
  n_stft = NULL
)

Arguments

n_mels	(int, optional): Number of mel filterbanks. (Default: 128)
sample_rate	(int, optional): Sample rate of audio signal. (Default: 16000)
f_min	(float, optional): Minimum frequency. (Default: 0.)
f_max	(float or NULL, optional): Maximum frequency. (Default: sample_rate // 2)
n_stft	(int, optional): Number of bins in STFT. Calculated from first input if NULL is given. See n_fft in :class:Spectrogram. (Default: NULL)

Details

forward param: specgram (Tensor): Tensor of audio of dimension (..., freq, time).

Value

tensor: Mel frequency spectrogram of size (..., n_mels, time).

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