Wildlife Audio Classification

One thing I've been really interested in lately is the wide range of wildlife sounds that I hear all over the hills of where I've been living. Each season brings new sounds that I've never heard before: bizarre bird calls, frogs croaking together in loud intricate patterns and yipping howls…

Portland Rain Data Sonification

The rumors are true, it rains alot in Portland! This seems to be common knowledge, however I wanted to take a slightly different look at the weather. The City of Portland HYDRA Rainfall Network publishes the average rainfall data online from various rain gages placed around the city. I thought…

808 Drum Machine Resynthesis using NSynth

I've been enjoying the combination of deep learning and sound design as a hobby recently and wanted to checkout Magenta Nsynth's fastgen for resynthesis on a well known set of samples. The Roland 808 drum machine has a classic and unmistakeable sound so I thought this would be interesting to…

Deep Learning Aphex Twin

Can machines create art or music? This is the question that Google Brain's Magenta project has been actively exploring. Over the last couple of weeks I've been playing with various models provided by Magenta to see what kind of musical possibilities Neural Nets have to offer. Given my background with…

Neural Dialog Generation Using Adversarial Learning

For a recent assignment, I wanted to explore Neural Dialog Generation using Adversarial Learning. This is was based on a recent paper written by a group of researchers at Stanford (Li et al., 2017;) where they propose a solution for text-based GANs by framing it as a Reinforcement Learning task…