Iver Jordal

Pros: * Julius has fewer dependencies, and is a lighter dependency overall * Julius is much faster, and can run on GPU Cons: * Julius is more memory-hungry

AKA band stop filter

CI: Test multiple versions of pytorch and torchaudio

3

We currently have compatibility code for pytorch < 1.7 and torchaudio < 0.7 which the CI currently does not test. We should start doing this.

Implement equalizer transform

3

Change the spectrum. Boost some frequencies, maybe attenuate some frequencies.

Implement resample transform

9

https://github.com/adefossez/julius

Implement temporal masking

2

@nicofarr

@nicofarr torch-audiomentations works on tensors with shapes like (batch_size, samples) or (batch_size, channels, samples) How do you propose CutMix would work when replacing some of the audio in an audio...

https://github.com/asteroid-team/torch-audiomentations/pull/32/files/3d5d9293bb31716e8cbf21e064a85d879940f835#diff-f8aff5239b5132abfaddcbaa25a0342ec801e5f75e0b82f27757169fa5a82c68