SP-Tools – Machine Learning tools for drums and percussion (alpha)

For the last few years I’ve been working on ideas and approaches to using electrics in a realtime/low-latency context with acoustic drums/percussion. The most recent of these have been working with the FluCoMa Toolkit to do some of the things I was doing before (but better) as well as try out some new things altogether.

During that time I honed in and refined a lot of the settings, descriptors/parameters, and algorithm choices to get something that I felt performed really well. Even as compared to commercial alternatives.

I decided that once FluCoMa put out the v1 of their toolkit, I would try and wrap up a bunch of the ideas into a cohesive package that focused on the approaches that I’ve been working on. After pushing hard on it for the last few months, I feel I have something that I can put out there. It’s still in what I would consider an alpha stage, though everything is quite stable. I’m only really considering it alpha as I will likely add more objects/abstractions/approaches, refine the ones that are there, as well as get a sense of how people are using and want to use it and potentially tweak some of the structure.

So for now you can download the package here:

http://github.com/rconstanzo/sp-tools

I’ve also made a quick overview video that talks you through the basic idea of the package, shows off some more examples, and will hopefully get you going with it.

If you have any comments or questions, or run into any bugs/problems, feel free to drop me an email and/or create an issue on GitHub.