Full source separation tutorial
justinsalamon opened this issue · 0 comments
Right now the scaper tutorial includes a section about the source separation features, which I think is sufficient for the general tutorial.
It would be great to create a separate, dedicated, tutorial about using Scaper for source separation.
The goal would be to make it dead simple for a user to get started with scaper for source separation. For example we should include downloadable source material and scripts (or notebooks) so the user can follow the tutorial on their machine.
In terms of audio domains, I think it would be great to at least include data+code for speech separation (e.g. speech vs noise) and music source separation. If we can also include data+example for DCASE-style (env sound) source separation that would be great.