Eloi Moliner Juanpere
Eloi Moliner Juanpere
you may like to check this paper https://arxiv.org/abs/2209.14687
Hi, I'm not an author of this paper, but also working on bandwidth extension of music, so I'm very interested if you manage to apply this method to music signals....
Hi, I tried training it on MAESTRO, which consists of piano music, and the result was not much what I expected. Here you can see some spectrograms:  and here...
Hi, The model was trained with the MusicNet dataset, which is mostly classical music. What kind of music recordings are you thinking about?
I think so. I did not apply any music-specific assumptions apart from the dataset, if this is what you mean. So if you train it with speech data it will...
Hi, Thank you for trying this model and the information. I'm aware that the memory consumption is quite suboptimal on this model. I would like to develop a more efficient...
Hi, this was meant to represent any kind of noisy input audio file that you would like to process. You can try, for example, with the ones uploaded in our...
Hi, I'm not sure I understand the issue. Do you mean that the norm should be squared? If so, note that after normalizing the gradients with the gradient norm, both...
Oh yes, you are right. That looks like a typo.
Hi, Sorry for the delay. Unfortunately, the cqt_nsgt_pytorch package broke some time ago, I don't have time to debug and fix the issue. In this other repository, I am using...