Over the past few months I've been working on a new PyTorch & Tensorflow project, which makes use of the NSynth Dataset. The goal with this project is to be able to generate sounds based on a written description, similar to the famous DALL·E project, wich synthesises images from text. There's still much to be done, but recently I've completed the CNN classifier, which allows to categorise 23 different sounds with a pretty decent accuracy. I'm very excited by all the new things I need to learn to continue with this project, and will post here as soon as I have my first usable results!
This week I started working on my liveset again, and I have to say after a year in the studio this has been a very welcome development. It took some time to get into performing again, especially with all the different buts & pieces involved. Currently I'm working with SuperCollider, Ableton and Lemur to assemble a completely new performance based on existing songs and live improvisation, which has been pretty exciting so far! Feel free to check out my Instagram account for more updates and some teasers of what's to come!
After about a year I'm very excited to share with you that my "Ms. You" EP is now available on all platforms!