« somasticks » are AI-augmented drumsticks that seek to emphasize the somatic side of drumming practice.

The sticks do not need to hit any physical objects to produce sound; rather, they may be waved in the air using gestures based on internal sensations to generate sounds, with the support of online learning techniques and wavelet analysis for continuous motion adaptation.

The current prototype equips standard drumsticks with R-IoT embedded systems, to which we connected two interruptors and a strain gauge for additionnal controls over machine learning techniques. The firmware is coded in C++ using the Energia platform; data is processed in Max/MSP using the MuBu toolbox, with wavelet analysis and online gaussian mixture models for motion, and concatenative synthesis for sound. somasticks are currently used in the daim art project.

music device
data design


The project was developed with Frédéric Bevilacqua, Riccardo Borghesi, Djellal Chalabi and Emmanuel Flety in collaboration with the ISMM group of IRCAM, in the context of the Sorbonne Université Doctorate in Computing.

movA workshop (April 2019)

Available on GitHub

Ce diaporama nécessite JavaScript.