transform_frequencymasking

Apply masking to a spectrogram in the frequency domain.

Provides access to datasets, models and processing
facilities for deep learning in audio.

Sigrid Keydana

torchaudio

R Interface to 'pytorch''s 'torchaudio'

Athos Damiani

Daniel Falbel

transform_frequencymasking function

<dl><dt>freq_mask_param</dt>
<dd>(int): maximum possible length of the mask.
Indices uniformly sampled from [0, freq_mask_param).</dd>
<dt>iid_masks</dt>
<dd>(bool, optional): whether to apply different masks to each
example/channel in the batch. (Default: <code>FALSE</code>)
This option is applicable only when the input tensor is 4D.</dd></dl>

Arguments

Frequency-domain Masking — transform_frequencymasking

<dl>

<dt>freq_mask_param</dt>
<dd>(int): maximum possible length of the mask.
Indices uniformly sampled from [0, freq_mask_param).</dd>


<dt>iid_masks</dt>
<dd>(bool, optional): whether to apply different masks to each
example/channel in the batch. (Default: <code>FALSE</code>)
This option is applicable only when the input tensor is 4D.</dd>

</dl>

transform_frequencymasking: Frequency-domain Masking

Description

Usage

Value

Arguments