Convolution operations in your model

[rruizdeaustri]

Dear authors,

I find quite interesting your work and I want to try it using my own data. Before that I'm trying to understand the details of your code and I got some confusion.
In the paper, you claim that you apply some 1D convolutions: "The decoder uses a transposed convolution layer for the element-wise multiplying of the mask matrix and an encoded representation to reconstruct the extracted signal". However, I don't find any convolution applied in the code you provide in github.
Could you please clarify it ?

Thanks a lot !

Roberto