_ Software

View on Github

Marcelle

Marcelle is a modular open source toolkit for programming interactive machine learning applications. Marcelle is built around components embedding computation and interaction that can be composed to form reactive machine learning pipelines and custom user interfaces. This architecture enables rapid prototyping and extension. Marcelle can be used to build interfaces to Python scripts, and it provides flexible data stores to facilitate collaboration between machine learning experts, designers and end users.

CO/DA

Coda.js is a javascript library and live-coding environment dedicated to the design of bodily interactions with audio processing. CO/DA was designed to support an improvisation practice involving dance and live coding, and it is focused on the real-time manipulation of continuous streams of the dancers’ motion data for interactive sound synthesis.

Gestural Sound Toolkit

The toolkit gathers a collection of Max/MSP patches and objects for easy and fast gesture-to-sound scenarios prototyping. It includes receivers from motion capture systems, signal processing modules, machine learning modules, and sound synthesis modules. Overview patch on the right.

XMM

Dual (GPLv3 + Commercial)

XMM is an open-source C++ library for continuous motion recognition and mapping. XMM is a portable, cross-platform C++ library that implements Gaussian Mixture Models and Hidden Markov Models for recognition and regression. The XMM library was developed for movement interaction in creative applications and implements an interactive machine learning workflow with fast training and continuous, real-time inference.

MuBu & PiPo

I contributed to the development of MuBu and PiPo, a libary of Max objects created in the {Sound Music Movement} Interaction team at ircam. I developed a max implementation of XMM that communicates with MuBu, as well as several PiPo signal processing modules.

Max Externals

I developed several (now unmaintained) Max externals, including myo for Max is a max external for communication with the Myo armband. Compatibility: Mac OS X 10.8+, Max 6.1+, 64-bit only. It is based on the Myo c++ API by Thalmic Labs. This object should be compiled with Max SDK version 6 or greater.