![]() The Wekinator: Software for using machine learning to build real-time interactive systems by Rebecca Fiebrink, Dan Trueman, and Perry Cook The Wekinator is a free
software package
to facilitate rapid
development of and experimentation with machine learning in live music
performance and other real-time domains. The Wekinator allows users to build interactive systems by
demonstrating human actions and computer responses, rather than by
programming.
Example applications:
The Wekinator includes:
get it & use it Instructions for downloading, running, and implementing your own add-ons are here Requires ChucK version 1.2.1.2 or later and Java version 5 or later
New user? Need help? Join the Wekinator users mailing list Just want occasional announcements about new releases? Join the announcement list introductory videos
Quick overview by Rebecca Fiebrink, using webcam and USB game controller to control ChucK and Max/MSP (September 2010) Demo by Phoenix Perry, using Kinect to control Unity game engine (January 2011) compositions using Wekinator Clapping Machine Music Variations (CMMV) by Dan Trueman Wekinator is used to create various new musical instruments, including one that controls the blotar physical modeling synthesis algorithm using the Real World Golf USB controller website Performances: 3 April 2010 - PLOrk Spring Concert: watch 5 June 2010 - Sideband @ International Computer Music Conference 25 July 2010 - SO Percussion Summer Institute: watch G by Raymond Weitekamp Laptop performers hit their laptops in different locations; based on the hit location detected by Wekinator, ChucK plays different sounds Performances: 3 April 2010 - PLOrk Spring Concert: watch 15 May 2010 - PLOrk final extravaganza The Gentle Senses by Michelle Nagai website The performer plays an instrument consisting of a piece of tree bark with embedded light sensors; the Wekinator translate light patterns into sound in Max/MSP Performances: 27 April 2010: Michelle Nagai at Princeton University blinky by Rebecca Fiebrink A piece for laptop orchestra and optional shakuhachi, in which performers control sound in ChucK by gesturing with flashlights in front of laptop webcams Performances: 19 April 2009: PLOrk at HASTAC, Chicago 16 May 2009 - PLOrk Spring Concert with special guest Riley Lee : watch 10 October 2009 - PLOrk at MMiX NYC nets0 by Rebecca Fiebrink A real-time machine learning improvisation, in which performers create mappings from controllers to sound from scratch and evolve them throughout the piece January 2009 - Princeton University: watch publications Fiebrink, R., P. R. Cook, and D. Trueman. "Human model evaluation in interactive supervised learning." Proceedings of the SIGCHI Conference on Human-Computer Interaction (CHI'11), Vancouver, BC, May 7-12, 2011. Fiebrink, R. Real-time Human Interaction with Supervised Learning Algorithms for Music Composition and Performance. PhD dissertation, Princeton University, 2011. Fiebrink, R., D. Trueman, C. Britt, M. Nagai, K. Kaczmarek, M. Early, M.R. Daniel, A. Hege, and P. R. Cook. “Toward understanding human-computer interaction in composing the instrument.” Proceedings of the International Computer Music Conference (ICMC), New York City, June 1–5, 2010. Fiebrink, R., P. R. Cook, and D. Trueman. "Play-along mapping of musical controllers." Proceedings of the International Computer Music Conference (ICMC), Montreal, August 4–9, 2009. Fiebrink, R., D. Trueman, and P. R. Cook. "A meta-instrument for interactive, on-the-fly machine learning." Proceedings of the International Conference on New Interfaces for Musical Expression (NIME), Pittsburgh, June 4–6, 2009. Wekinator Users Hall of Fame Andrew McPherson Anne Hege Cameron Britt Dan Trueman Konrad Kaczmarek Meg Schedel Michelle Nagai Michael Early M. R. Daniel Phoenix Perry Raymond Weitekamp Students of PLOrk 2010 Thanks to everyone above for making cool projects and sharing their feedback! see also Wekintor on Google Code weka - from the University of Waikato Rebecca Fiebrink's homepage |