Utils for ReSpeaker Microphone Array. It includes DOA (Direction of Arrival), VAD (Voice Activity Detection), KWS (Keyword Spotting or Keyword Search) and etc.
pixel_ring.py
- control the pixel ringmic_array.py
- read 8 channels raw audio from the Mic Array and estimate sound's DOA (Direction of Arrival)vad_doa.py
- do VAD (Voice Activity Detection) and then estimate DOAkws_doa.py
- search keyword and then estimate DOA
-
For ReSpeaker USB Mic Array - Far-field w/ 7 PDM Microphones
Change the Mic Array's firmware to get 8 channels raw audio. See https://github.com/respeaker/mic_array_dfu
-
For 4 Mic Array Pi hat
Install seeed-voicecard driver first. Change
CHANNELS = 8
toCHANNELS = 4
in vad_doa.py and kws_doa.py
-
Run
pixel_ring.py
to control the pixel ring of the Mic Array through USB HIDsudo pip install pyusb sudo python pixel_ring.py
If you don't want to access USB device with
sudo
, add a udev.rules
file to/etc/udev/rules.d
:echo 'SUBSYSTEM=="usb", MODE="0666"' | sudo tee -a /etc/udev/rules.d/60-usb.rules sudo udevadm control -R # then re-plug the usb device
-
Read 8 channels audio from the Mic Array and estimate sound's DOA
sudo apt-get install python-numpy # or pip install numpy python mic_array.py
-
Do VAD and then estimate DOA
sudo pip install webrtcvad python vad_doa.py
-
Do KWS and then estimate DOA
Get snowboy work and run
python kws_doa.py
git submodule init git submodule update cd snowboy/swig/Python sudo apt-get install python-dev libatlas-base-dev swig # requiremetns to compile snowboy make # if got an error of swig3.x.x, edit the Makefile and disable the swig version check. echo 'from snowboydetect import *' > __init__.py # create __init__.py for a python module cd ../../.. # chang to the root directory of the repository ln -s snowboy/swig/Python snowboydetect python kws_doa.py
Google released Google Assistant Library for Raspberry Pi to provide hotword detection ("Ok Google" or "Hey Google"), audio recording, assistant response playback and etc. We can add LED lights indicator based on the library to make a device very similar with Google Home.
- Follow the guide to install Google Assistant Library.
- Run
python google_assistant_for_raspberry_pi.py
ODAS is a very cool project to perform sound source localization, tracking, separation and post-filtering. Let's have a try!
- get ODAS and build it
sudo apt-get install libfftw3-dev libconfig-dev libasound2-dev
git clone https://github.com/introlab/odas.git --branch=dev
mkdir odas/build
cd odas/build
cmake ..
make
- get ODAS Studio from https://github.com/introlab/odas_web/releases and open it. You can run ODAS Studio on a computer or the Raspberry Pi
The odascore
will be at odas/bin/odascore
, the config file is at odas.cfg. Change odas.cfg
based on your sound card number.
interface: {
type = "soundcard";
card = 1;
device = 0;
}
If you run the ODAS Studio on a computer, you should also need to change IP address from 127.0.0.1
to the IP of the computer.