![[Research] Creating Latent Representations of Synthesizer Patches using Variational Autoencoders](/assets/latent_reps.2058a50a_d1Re1.png)
[Research] Creating Latent Representations of Synthesizer Patches using Variational Autoencoders
This research introduces two ways of representing synthesizer patches using the latent space of a Variational Autoencoder.
My name is Matt Peachey. I am a PhD student in the Faculty of Computer Science at Dalhousie University, in Halifax, Canada. I am currently working on research projects involving Machine Learning, Human Computer Interaction, and Music.
This page is used to share my thoughts on research, technology, music, sports and more. Take a look around!
Here I'm demoing one of my projects that uses Google's MediaPipe Hands for ML powered motion-capture for hand-tracking and uses that data to control parameters of a digital synthesizer in real time.
This research introduces two ways of representing synthesizer patches using the latent space of a Variational Autoencoder.
FAUSTMapper is a lightweight binding between arbitrary FAUST-based audio projects and the mapping middleware, libmapper.
I participated along side Shannon Myles in two "Ocean of Data" challenges, where we developed innovated solutions to specific ocean related problems. We were proud to be awarded the top entry in both challenges.
This blog post provides a little bit of context about who I am & what I'm interested in. Take a read to learn more!