MSc Course Projects 1: Direction of Voice Filter

I’ve just finished my first year of my Master’s program and I’ve so far done a couple of course projects in a variety of areas. This is the Direction-of-Voice filter, which I’ve done with my colleague Abi Kuganesan for Dr. Robert Xiao’s “Machine Learning for Signal Processing” course. It’s an audio filtration application that filters unintended voice audio out of an audio signal by using machine learning to eliminate the portions of the audio generated by speakers not facing the microphone. Please also check out our presentation and demo that I’ve uploaded to YouTube!

The full report is also available on GitHub as well.