# Onset-based regression (JIT-MFCC example)

**URL:** https://discourse.flucoma.org/t/onset-based-regression-jit-mfcc-example/464
**Category:** Pre-Release Toolbox2 New Ideas
**Created:** [April 26, 2020, 2:51pm UTC](https://discourse.flucoma.org/t/onset-based-regression-jit-mfcc-example/464 "2020-04-26T14:51:09Z")
**Posts on this page:** 1
**Showing post:** 45

<div class="post-metadata">

### Author: ![rodrigo.constanzo](https://discourse.flucoma.org/user_avatar/discourse.flucoma.org/rodrigo.constanzo/32/12_2.png) [@rodrigo.constanzo](https://discourse.flucoma.org/u/rodrigo.constanzo)
#### Post date: [May 12, 2020, 10:55am UTC](https://discourse.flucoma.org/t/onset-based-regression-jit-mfcc-example/464/45 "2020-05-12T10:55:18Z")

</div>

I was reminded today of the [oldschool NMF-as-KNN approach](https://discourse.flucoma.org/t/pre-processing-for-training-for-real-time-nmf/145) I was experimenting with early in the process, and came across [this post](https://discourse.flucoma.org/t/pre-processing-for-training-for-real-time-nmf/145/19) which shows how effective `@filterupdate 1` was at refining the filters and selections.

> [@Pre-processing for (Training for real-time NMF)](https://discourse.flucoma.org/t/pre-processing-for-training-for-real-time-nmf/145/19):
>
> First, a little bump (for @tremblap) about extracting an IR from an audio file, as it would be good to revisit the filtering aspect of this process. And more excitingly, the new(ly fixed) @filterupdate 1 is having some nice results on my dicts. Just the raw @ranks: And some @filterupdate 1 with @iterations 1000: I still haven’t tested the matching itself (for reasons expressed elsewhere), but this is a promising step. I also want to test out what @groma suggested in …

Pre `@filterupdate 1`:  
 ![c33695207779208bcf68c9d3b43094a81ca042c7_2_397x500](https://discourse.flucoma.org/uploads/default/original/1X/6fb809a42866ee7e088154cecd9d136b4f3776b0.jpeg)

Post `@filterupdate 1`:  
 ![16237701609a34a8fc6c56ff514caee296d60960_2_397x500](https://discourse.flucoma.org/uploads/default/original/1X/e372d9b568e1fde2f39342d7298ba2f8d8851131.png)

I’m (fairly) certain this is a naive question, which is probably not possible given the algorithms at play, but is there a way to train some points, and then run arbitrary audio through to have it refine the selections based on the input?

Obviously one can add more points to each classification, but perhaps something like this could help catch or fix the edge cases. (Would be amazing if there was a 2d view where the arbitrary audio that it was fed is mapped, and you could go through and say “this point is A, this point is B” and have the network update accordingly.

---

_[View the full topic](https://discourse.flucoma.org/t/onset-based-regression-jit-mfcc-example/464)._