Music Information Retrieval Algorithms for Oral History Collections

Digital humanities, as a largely a text based domain, often treats audio files as texts, retrieving semantic information in order to categorise, sort, and discover audio. This workshop enabled participants to treat audio as audio. Taking oral history collections from the University of Sussex Resistance Archive as a test case, participants were lead through the use of Music Information Retrieval (MIR) approaches to categorise, sort, and support their discovery of an audio collection. Participants were also supported in planning the extension of these approaches to audio collections that they know or work with.

Included in this deposit are:

• introductory slides
• a zipped Lubuntu virtual machine containing Jupyter notebooks

To work through the lessons using the virtual machine you need to:

• download the split .zip files
• reassembled the split .zip into a single .zip (using Unarchiver or similar) and unzip
• download and install VirtualBox
• point VirtualBox at the unzipped virtual machine
• load the virtual machine
• inside the virtual machine, open the Terminal, press up. It should now read 'jupyter notebook'. Hit enter and the notebook interface will open in the browser.
• Navigate to the lessons and work through them!

This workshop was lead in July 2016 by a team from the Sussex Humanities Lab. Any queries or questions, please contact shl@sussex.ac.uk