# Melbands vs MFCCs and "noise"

**URL:** <https://discourse.flucoma.org/t/melbands-vs-mfccs-and-noise/833>\
**Category:** Usage Questions\
**Created:** [March 14, 2021, 12:51am UTC](https://discourse.flucoma.org/t/melbands-vs-mfccs-and-noise/833 "2021-03-14T00:51:09Z")\
**Posts on this page:** 1\
**Showing post:** 3

<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:** [March 14, 2021, 2:48pm UTC](https://discourse.flucoma.org/t/melbands-vs-mfccs-and-noise/833/3 "2021-03-14T14:48:31Z")

</div>

> [@tremblap](#):
>
> gating the signal by amplitude to remove the quiet noisy frames and keep just those with valid signal in. That applies to MFCC but you could also do that on mel bands and normalise the result after to dismiss the amplitude and keep just the contour.

Interesting. On the short time scale there’s only 7 frames, and they all tend to have something. I even spent a bit over hour yesterday massaging the JIT analysis frame recording to make sure I capture as much of the attack (and tail) as possible. In the end I went with 16 samples _before_ the onset was detected, and that seemed to work the best. Visualizing and browsing the clustering post UMAP is what I used to here to assess the effectiveness. (You had suggested something similar ages ago, but other than comparing raw matching %, I had no meaningful way of knowing whether it was working).

> [@tremblap](#):
>
> denoising the signal by splitting it: HPSS or sines than analyse the pitched component.

This too is interesting. I was [exploring some pre-decomposed analysis stuff last year and got really good and promising results](https://discourse.flucoma.org/t/hybrid-vertical-layered-resynthesis/502). I just got slowed down on that by the amount of HD (and RAM) required. That could connect nicely with a decomposed input analysis as that could fork off there.

I hadn’t really considered doing this as a denoise-ing thing though.

> [@tremblap](#):
>
> autoencoder as denoiser, as proposed before. The bottleneck allows to remove the details to keep the gist, which is great if you think about it in this case as you train on a complete dataset.

I guess this will be an interesting thing to try, vs the UMAP I’m using for timbre at the moment. We’ll geek later this week and see how this goes.

---

_[View the full topic](https://discourse.flucoma.org/t/melbands-vs-mfccs-and-noise/833)._