torchaudio.prototype.functional.barkscale_fbanks

torchaudio.prototype.functional.barkscale_fbanks(n_freqs: int, f_min: float, f_max: float, n_barks: int, sample_rate: int, bark_scale: str = 'traunmuller') → Tensor

Create a frequency bin conversion matrix.

Parameters:

• n_freqs (int) – Number of frequencies to highlight/apply

• f_min (float) – Minimum frequency (Hz)

• f_max (float) – Maximum frequency (Hz)

• n_barks (int) – Number of mel filterbanks

• sample_rate (int) – Sample rate of the audio waveform

• bark_scale (str, optional) – Scale to use: traunmuller,``schroeder`` or wang. (Default: traunmuller)

Returns:

Triangular filter banks (fb matrix) of size (n_freqs, n_barks) meaning number of frequencies to highlight/apply to x the number of filterbanks. Each column is a filterbank so that assuming there is a matrix A of size (…, n_freqs), the applied result would be A * barkscale_fbanks(A.size(-1), ...).

Return type:

torch.Tensor