How to over engineer a sound classifier

Detecting a trivial sound in a quiet environment using deep learning.

⚠️ Note: You can jump to the complete blog post on my github pages blog; the first section is below.

🏡 Hack day idea

I recently moved our washing machine out to the garage, which meant that I couldn’t hear it beep when it was finished. I would have some “false positive” trips out there (through the drizzly British rain!) when timers went off, only to find that the thing was still going. How horrendous.

It had also been a while since I wrote some code just for the sake of building something and I had never done anything with software and sound (recording, cleaning, classification). So, solving this first world problem for myself became my small 💡 idea for a hack project I could work on as the world slowly started locking itself down.

This post is an overview of what I built. It does not cover the day that I spent dusting off the old laptop and generally waiting for all of the updates to download (goodbye, Python 2.7!). It also does not give appropriate credit to the infinite StackOverflow posts that I read along the way.

All of the code for this is on Github in my sound-detection repo.

🎧 Collecting training data

Jump over to my github blog to read the full post.