tf.signal is differentiable about nnaudio HOT 6 CLOSED

I think you were trying to say that it does not support a trainable basis? That's true, but it's still differentiable so you can incorporate it into a network and backpropagate through it (e.g. to add a spectral loss to model that generates time-domain waveforms -- as in Parallel WaveNet)

from nnaudio.

Nice job on this repo and the paper by the way :).

from nnaudio.

I think you were trying to say that it does not support a trainable basis? That's true, but it's still differentiable so you can incorporate it into a network and backpropagate through it (e.g. to add a spectral loss to model that generates time-domain waveforms -- as in Parallel WaveNet)

Thanks for pointing it out. You are right, I was talking about the trainable basis. I will fix the paper now.

from nnaudio.

Hi Ryan, I have removed the claim that tf.signal doesn't support backpropagation.
Can you check if it is better now?
https://arxiv.org/abs/1912.12055

from nnaudio.

Thanks a lot for updating it!

from nnaudio.

Hi. Can I ask what is meant by trainable basis?
I came across this issue while googling around to see whether I could optimize tf.signal.stft's frame_length and frame_step parameters along with all the other parameters of my network, through backprop. Would this be technically possible?

from nnaudio.