ECS researcher to undertake first Internet-scale musical analysis

ECS Professor David De Roure is one of the principal researchers in a new project which enables the online analysis of a wide variety of music from all over the world.

The Structural Analysis of Large Amounts of Music Information (SALAMI) project, which involves academics from the School of Electronics and Computer Science (ECS) and international partners, has been funded by three leading research agencies to deliver a very substantive web-accessible corpus of musical analyses in a common framework for use in particular by music scholars and students.

The funding was awarded under the Digging into Data Challenge Competition and announced last week in Ottawa, Canada. The programme’s funders are the Joint Information Systems Committee (JISC) from the United Kingdom, the National Science Foundation (NSF) from the United States, and the Social Sciences and Humanities Research Council (SSHRC) from Canada

This project will make it possible to embark on a significant exercise in musical analysis involving up to 350,000 songs.

'To date, musical analysis has been conducted by individuals on a small scale,' said Professor David De Roure, who is a Professor of Computer Science in ECS and a keen musician with a background in music retrieval.

'This innovative project means that the range of music analysed will be of far larger variety than anything previously done. Previous analytic research work focused primarily on Western popular and classical music. Our vast dataset includes a wide variety of music from all over the world, from many time periods, and includes folk, classical, contemporary, improvised, and live music.'

Over an intensive 15-month period, the team will use a set of algorithms and tools for extracting features from recorded music and produce an open source dataset for thousands of pieces of music which will provide a rich resource for music scholars, providing new perspectives and insights previously unavailable.

The University of Southampton will develop SALAMI with the University of Illinois at Urbana-Champaign and the Schulich School of Music, McGill University. The US National Center for Supercomputing Applications (NCSA) has donated thousands of hours of processing time, and other collaborators include the Internet Archive and the BBC.