This module for Node-RED contains a set of nodes which offer audio feature extraction functionalities. Such nodes have a python core that runs on Librosa library.
Be sure to have a working installation of Node-RED.
Install python and the following libraries:
To install the stable version use the Menu - Manage palette option and search for node-red-contrib-audio-feature-extraction, or run the following command in your Node-RED user directory (typically ~/.node-red):
npm i node-red-contrib-audio-feature-extraction
These are a few examples of what can be done with this package.
Flows and a test audio file are available in the 'test' folder. Make sure that the paths specified inside nodes' configurations are correct before trying to execute the program.
Tip: you can run 'node-red' (or 'sudo node-red' if you are uning linux) from the folder '.node-red/node-modules/node-red-contrib-audio-feature-extraction' and the paths will be automatically correct.
Sampling audio file, computing stft, extracting mfcc and saving csv file.
Saving wav recieved from mqtt.
Extract chroma from stft recieved from serial port.
Multiple features can be extracted at the same time.
When no persistance and no wav nodes are present, the result is returned by the last block. In this example the STFT is printed.
Warning: each node of this library appends its configurations to the msg object. Only the last node in a flow will carry out all the computations according to all configurations.
Example flows available here: