Ivan Beskrovny

@vlsergey https://github.com/vlsergey/infosec/pull/5827 - fixed

> @vivekkhandelwal1 @silvasean, thank you so much for you quick and nice answers! > I also think decomposition solution is better than to define a LSTM op for backend. >...

Sorry for necroposting here, but I'm trying to train this model, and with no luck yet. I managed to add trainable PCEN (as described in paper) and training on spectrograms....

> Hi @JBloodless , > > In my case I am using Conv1d, but I decided to change original losses for a GAN since they weren't quite working for me...

@eagomez2 I'm assuming that you using your code above to calculate complex mask and then multiplying this with complex input to produce output waveform, is this correct?

> > @eagomez2 I'm assuming that you using your code above to calculate complex mask and then multiplying this with complex input to produce output waveform, is this correct? >...