Working on a real-time audio classifier recently, I keep noticing how the gate-before-processing pattern from this era still rules modern audio ML. Feed silence into a sound classifier and it'll happily hallucinate something — so you put a noise gate on the input, exactly like the trick described here, just used for a different purpose.

Counterintuitive thing I learned: when I tried to skip the explicit gate and 'let the model learn it', accuracy dropped meaningfully. The deterministic preprocessing wins over end-to-end here. Kind of an inverse of Padgham's 'accident becomes intent' — the technique survives, just on the analysis side now instead of the production side.

I don't know why you were flagged because this is quite relevant to the discussion .. it should be noted that this gated processing technique is quite common and not just for bass/drums - its also used in M/S techniques for recording vocals, acoustic instruments, and so on. I hope you'll train your classifier on different targets of the technique - it seems that would be fruitful, in terms of getting a classifier applied in new ways ..