jonnor/ESC-CNN-microcontroller
Environmental Sound Classification on Microcontrollers using Convolutional Neural Networks
This project helps urban planners and environmental scientists monitor noise pollution more effectively. It takes raw audio recordings from sensors and classifies the type of sound (e.g., car, dog bark, drilling) directly on the sensor itself, rather than sending all audio to a central server. This allows for real-time identification of noise sources, helping to understand and mitigate urban noise problems while preserving privacy.
106 stars. No commits in the last 6 months.
Use this if you need to identify specific noise sources in urban environments using low-power, cost-effective sensor networks without transmitting raw audio data.
Not ideal if your primary goal is simple sound level monitoring without needing to classify the type of noise, or if you have ample power and network bandwidth to send full audio to cloud systems.
Stars
106
Forks
19
Language
Jupyter Notebook
License
—
Category
Last pushed
Aug 02, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jonnor/ESC-CNN-microcontroller"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
aqibsaeed/Urban-Sound-Classification
Urban sound classification using Deep Learning
spotify/realbook
Easier audio-based machine learning with TensorFlow.
ArmDeveloperEcosystem/ml-audio-classifier-example-for-pico
ML Audio Classifier Example for Pico 🔊🔥🔔
IliaZenkov/sklearn-audio-classification
An in-depth analysis of audio classification on the RAVDESS dataset. Feature engineering,...
mimbres/neural-audio-fp
Official implementation of Neural Audio Fingerprint (ICASSP 2021)