https://github.com/jonnor/brewing-audio-event-detection

Tracking beer/wine using Audio Event Detection with Machine Learning
https://github.com/jonnor/brewing-audio-event-detection

Last synced: about 1 year ago
JSON representation

Tracking beer/wine using Audio Event Detection with Machine Learning

• Host: GitHub
• URL: https://github.com/jonnor/brewing-audio-event-detection
• Owner: jonnor
• Created: 2021-04-07T20:36:57.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2024-06-16T22:52:47.000Z (about 2 years ago)
• Last Synced: 2025-04-19T14:58:30.573Z (over 1 year ago)
• Language: Jupyter Notebook
• Size: 8.43 MB
• Stars: 14
• Watchers: 5
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          

# Tracking brewing using Audio Event Detection with Machine Learning

The fermentation process is critical when brewing alcoholic bewerages such as wine, cider, and beer.

To check that the fermentation is progressing OK one should pay attention to the activity of the airlock.

This repository shows how one can use Machine Learning to listen and cound the bubble "plops" of the airlock,

to track the fermentation activity.

Note: This is part of a **tutorial** on [Machine Learning for Audio Event Detection](https://github.com/jonnor/machinehearing/tree/master/geekleml2021).

It is *not intended* to be a replacement for a proper fermentation tracking system.

If you just want something that works for fermentation tracking,

get a [Plaato Airlock](https://plaato.io/products/plaato-airlock).

Or if you want to build something yourself, consider a [BrewBubbles](https://docs.brewbubbles.com/) bubble counter or a [iSpindle](https://www.ispindel.de) hydrometer.

If you want to learn about [Machine Learning for Audio]((https://github.com/jonnor/machinehearing)), this is for you!

This repository will serve as a simple example of a practical audio ML system,

using Audio Event Detection.

It should be a good starting point for developing similar application.

![Soundsensing logo](./img/soundsensing-banner.png)

This project is sponsored by [Soundsensing](https://soundsensing.no)

provider of IoT audio sensors with built-in Machine Learning,

used for Noise Monitoring and Condition Monitoring.

The sensors are ideal for continious monitoring of audible noises and events,

and can perform tasks such as Audio Classification, Audio Event Detection and Acoustic Anomaly Detection.

Their sensors can transmit compressed and privacy-preserving spectrograms,

allowing Machine Learning to be done in the cloud using familiar tools like Python.

Or models can be deployed onto the sensor itself, for a highly efficient on-edge ML solution.