Pre-processing for (Training for real-time NMF)

[rodrigo.constanzo]

@tremblap

I don’t understand what you try to get? The dicts are filter design already, i.e. the amplitude of each FFT bin. What do you want to do exactly?

The IR question(s) are about cleaning up the noisy audio from the fancy drum trigger, not the dicts. The dicts, as far as I can tell are fine.

@tremblap

Then i would probably take the noise, and use the HIRT to make an FIR filter, if I was not getting the results I wanted.

Basically this. What’s the step for going from noise to FIR with HIRT?

@tremblap

I still haven’t tested the matching itself (for reasons expressed elsewhere)

?

Actually I crossed my threads!

My last comment was referring to the discussion from the Training for real-time NMF thread.

Basically the problem of being able to grab the correct frame from the output of fluid.nmfmatch~ to compare against. At the moment none of what I have actually works. I’m just building good (theoretical) dicts so that I can improve the likelihood of getting accurate matching from fluid.nmfmatch~, but since I have no way of assessing the improvements, I’m just shooting in the dark.

You did tease that you had some ideas for this, if I understood you right.