[jimbooonooo]

Howdy all,

Recently, a friend and I were joking about ways to ignore unpleasant voices at a family BBQ. A quick look at current speech detection methods led down a rabbit-hole (of course), and resulted in this fun proof of concept.

I was surprised at how well speaker embedding performed (and also acknowledge the sparse, subjective nature of my results).

It was a fun weekend project, and I hope you enjoy the write up!