Assume you're using a respeaker_usb_4_mic_array (v2).

docker pull ghcr.io/bigjohnn/docker-odas:latest
git clone git@github.com:BigJohnn/odas.git
cd docker
sudo docker compose up

tty1:

docker exec -it docker-odas-1 /bin/bash
python3 DOA_sound.py

tty2:

docker exec -it docker-odas-1 /bin/bash
sudo ./build/bin/odaslive -c config/odaslive/respeaker_usb_4_mic_array.cfg

Enjoy!

Or you can build it from scratch, please read the codes in docker_dev and/or docker_runtime for more information.

ODAS stands for Open embeddeD Audition System. This is a library dedicated to perform sound source localization, tracking, separation and post-filtering. ODAS is coded entirely in C, for more portability, and is optimized to run easily on low-cost embedded hardware. ODAS is free and open source.

The ODAS wiki describes how to build and run the software.

ROS: Please visite the odas_ros project.

ODAS is provided with the MIT license.

Please have a look at the odas_web project.

• 8SoundsUSB, 8 inputs, USB powered, configurable microphone array.
• 16SoundsUSB, 16 inputs, USB powered, configurable microphone array.

You can find more information about the methods implemented in ODAS in these papers:

• F. Grondin, D. Létourneau, C. Godin, J.-S. Lauzon, J. Vincent, S. Michaud, S. Faucher, F. Michaud, ODAS: Open embeddeD Audition System, Frontiers in Robotics and AI, Volume 9, 2022

• F. Grondin and F. Michaud, Lightweight and Optimized Sound Source Localization and Tracking Methods for Opened and Closed Microphone Array Configurations, Robotics and Autonomous Systems, 2019