RobertoAlessandri/CNN_DOA
Test of the ability of a Convolutional Neural Network (CNN) trained to localize the Direction Of Arrival (DOA), to generalize in different environments.
This project helps acoustic engineers and researchers evaluate how well a deep learning model can pinpoint the direction of a sound source in various real-world settings. You provide recorded sound data from a small microphone array, and the system outputs predictions about where the sound originated. This is ideal for professionals developing or deploying sound localization systems.
No commits in the last 6 months.
Use this if you need to test the robustness of a sound source localization model's predictions when environmental factors like room size, microphone placement, or sound source distance change.
Not ideal if you are looking for an out-of-the-box solution to localize sound in live environments without needing to evaluate model generalization.
Stars
18
Forks
4
Language
Jupyter Notebook
License
—
Category
Last pushed
Jul 14, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/RobertoAlessandri/CNN_DOA"
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 🔊🔥🔔
mimbres/neural-audio-fp
Official implementation of Neural Audio Fingerprint (ICASSP 2021)
f4exb/morseangel
Deep Neural Network for Morse decoding