Companion software tutorial for the following article:
E. J. Humphrey, S. Reddy, P. Seetharaman, A. Kumar, R. M. Bittner, A. Demetriou, S. Gulati, A. Jansson, T. Jehan, B. Lehner, A. Kruspe, L. Yang. "An Introduction to Singing Voice Analysis" IEEE Signal Processing Magazine, Special Issue on Music Signal Processing. January 2019.
The article is available online via IEEE Xplore.
This repository contains three Jupyter notebooks demonstrating machine learning approaches to tackling three different vocal analysis tasks.
- Tutorial 1 - Vocal Activity Detection
- Tutorial 2 - Vocalist ID and Similarity
- Tutorial 3 - Sung Language ID
More detailed instructions to follow, but the necessary dependencies are listed in the requirements.txt
file.
Please note that these tutorials are meant to serve as light guidance toward tackling different challenges in singing voice analysis, and are in something resembling an alpha state currently.
If you run into any difficulties, feel free to create issues here, or join the MIR Slack Community and drop into the #audio-analysis channel.