# Realtime Classification of Hand-Drum Strokes - old NIME paper

**URL:** https://discourse.flucoma.org/t/realtime-classification-of-hand-drum-strokes-old-nime-paper/863
**Category:** Learning Resources
**Created:** [April 12, 2021, 8:41am UTC](https://discourse.flucoma.org/t/realtime-classification-of-hand-drum-strokes-old-nime-paper/863 "2021-04-12T08:41:01Z")
**Posts on this page:** 1
**Page:** 1

<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: [April 12, 2021, 8:41am UTC](https://discourse.flucoma.org/t/realtime-classification-of-hand-drum-strokes-old-nime-paper/863/1 "2021-04-12T08:41:01Z")

</div>

Someone linked this over on the [lines forum](https://llllllll.co), in the [Kaizo Snare post](https://llllllll.co/t/kaizo-snare-performance-epic-blog-post/35387/11) I had made there and thought it would be posting here:

[![](https://img.youtube.com/vi/sJFPkKRQgLk/maxresdefault.jpg "Realtime Percussive Stroke Classifier") ](https://www.youtube.com/watch?v=sJFPkKRQgLk)

[https://www.nime.org/proceedings/2015/nime2015\_147.pdf](https://www.nime.org/proceedings/2015/nime2015_147.pdf)

The paper is a bit old now (2015), and he’s using 50ms analysis windows, with an FFT-based onset detector, so the exact implementation is orders of magnitude too slow for my purposes, but good to read through nonetheless.

Descriptor-wise it looks pretty vanilla: loudness, centroid, ZCR, and he talks about incorporating spread/skewness/kurtosis as well. Then beyond that it just goes into a kNN classifier.

I’m surprised it’s not 100% given the analysis window and sounds used (three very different cajon sounds), but it’s pretty good results (95%) either way.