This post presents early results for the Secret Sauce project. We show that it is possible to predict guitar effects accurately with high level audio features and recurrent neural nets, but predicting synthesizer patches is more challenging.
The aim of the Secret Sauce project is to automatically reverse engineer studio sounds, with a focus on guitar effects and synthesizers. Ultimately, we wish to answer the question
Wow, how did they make that sound?!. This post presents the task and makes the datasets available for whoever would like to try.
Plenty of people are interested in Machine Learning at Columbia, and therefore several concurrent reading groups and seminars have appeared. This page is an attempt to list them. Please do contact me for any update, remark or correction.