It has been one year since RAPID MIX began. Here we have collected our public documents for the first year of the RAPID MIX Project. These are downloadable PDFs outlining the thought, work and planning behind the various aspects of the project.
RAPID MIX team member Rebecca Fiebrink has launched a new version of the machine learning software, Wekinator, an incredibly powerful yet user friendly toolkit for bringing expressive gestures into your music, art, making, and interaction design. This is a major new version that includes dynamic time warping alongside new classification and regression algorithms. You can download it here (for mac/windows/linux) along with many new examples for connecting it to real-time music/animation/gaming/sensing environments: www.wekinator.org. The technology that drives Wekinator will feature in many RAPID MIX products that you’ll be hearing about in the future.
The launch coincides the launch of a free online class run by Rebecca, Machine Learning for Musicians and Artists: https://www.kadenze.com/courses/machine-learning-for-musicians-and-artists/info. If you’re interested in machine learning for building real-time interactions, sign up! No prior machine learning knowledge or mathematical background is necessary. The course is probably most interesting for people who can already program in some environment (e.g., Processing, Max/MSP) but should still be accessible to people who don’t. The course features two guest lecturers, music technology researcher Baptiste Caramiaux and composer/instrument builder/performer Laetitia Sonami.
Lecture topics will include:
• What is machine learning?
• Common types of machine learning for making sense of human actions and sensor data, with a focus on classification, regression, and segmentation
• The “machine learning pipeline”: understanding how signals, features, algorithms, and models fit together, and how to select and configure each part of this pipeline to get good analysis results
• Off-the-shelf tools for machine learning (e.g., Wekinator, Weka, GestureFollower)
• Feature extraction and analysis techniques that are well-suited for music, dance, gaming, and visual art, especially for human motion analysis and audio analysis
• How to connect your machine learning tools to common digital arts tools such as Max/MSP, PD, ChucK, Processing, Unity 3D, SuperCollider, OpenFrameworks
• Introduction to cheap & easy sensing technologies that can be used as inputs to machine learning systems (e.g., Kinect, computer vision, hardware sensors, gaming controllers)
We’re excited to announce more media coverage of the Kurv Guitar, one of the first commercial products to be powered by RAPID MIX technologies, on Sky News “Swipe” show, as part of a special on new musical instruments. You can watch it here:
NOISE is the most full-bodied instrument to ever hit the glass surface of an iPhone. It turns the iPhone screen into a continuous sonic surface that responds to the subtlest gestures. Taking advantage of the new 3D Touch technology of the iPhone 6s, the surface lets music-makes shape sound through Strike, Press, Glide, Slide, and Lift – the “Five Dimensions of Touch” that customers and critics have celebrated on ROLI’s award-winning Seaboard RISE.
As an instrument NOISE features 25 keywaves, includes 25 sounds, and has five faders for fine-tuning the touch-responsiveness of the surface. It is now available for music-makers of any skill level who want to explore a multidimensionally expressive instrument that fits in their pockets.
NOISE is also the ultimate portable sound engine for the Seaboard RISE and other MIDI controllers. Powered by Equator and using MIDI over Bluetooth, NOISE lets music-makers control sounds wirelessly from their iPhones. It is one of the first apps to enable Multidimensional Polyphonic Expression (MPE) through its MPE Mode, so the NOISE mobile sound engine works with any MPE-compatible controller. ROLI’s sound designers have crafted the app’s 25 preset sounds – which include Breath Flute and Extreme Loop Synth – especially for MPE expressivity. Additional sounds can be purchased in-app.
With a Seaboard RISE, a Flip Case, and NOISE on their iPhones, music-makers now have a connected set of portable tools for making expressive music on the go.
While it works with all models of iPhone from the iPhone 5 to the iPhone 6s, NOISE has been optimized to take full advantage of 3D Touch on the iPhone 6s.
At its heart is a powerful combination of RAPID MIX gesture recognition and synthesis technologies (such as Mick Grierson’s Maximilian library) along with our own hardware design and bluetooth firmware.
BITalino makers PLUX are one of the key industry partners working on the RAPID-MIX project, producing “Arduino”-like technologies specialised on body sensing and bio-hacking wearables prototyping. The RAPID-API will give multiple ways to use this information in new, creative ways.
As a result of the RAPID-MIX presence at the Barcelona Hack Day 2015, where hackers highlighted usability concerns associated with the typical wires, the team at BITalino has assimilated this feedback to release the new SnapBITS – “getting rid of the pesky electrode cables to make life easier for BITalino users”.
Check out their website for more information, and stay tuned to the RAPID-MIX blog to find out how we can help you creatively use these exciting technologies: