Description

The objective of the International Music Information Retrieval Systems Evaluation Laboratory(IMIRSEL) is the establishment of the necessary resources for scientifically valid development as well as evaluation of emerging Music Information Retrieval (MIR), Music Digital Library (MDL) techniques and technologies. One of the parts of IMIRSEL is the creation of secure, yet accessible, large-scale collections of music materials in a variety of audio, symbolic and metadata forms. These collections, when coupled with a set of standardized experimental tasks and standardized evaluation metrics, will allow members of the international MIR/MDL research community to participate in TREC-like evaluation tasks so they can scientifically compare and contrast their different approaches to making the world's vast store of musical heritage materials ever more available.

IMIRSEL is located at the Graduate School of Library and Information Science (GSLIS) at the University of Illinois at Urbana-Champaign (UIUC). The Head of the Laboratory is Prof.J. Stephen Downie from GSLIS.

Current IMIRSEL projects include:

  • Music Information Retrieval Evaluation eXchange (MIREX)

    MIREX represents an annual community-based MIR/MDL evaluation event where techniques and algorithms tailored to a variety of tasks are submitted by research laboratories from all over the world to IMIRSEL. These algorithms are then run along with standardized datasets, and evaluated using community-defined evaluation metrics. The evaluation results are published on a year basis and they are presented at the International Conference on Music Information Retrieval (ISMIR).

  • Networked Environment for Music Analysis (NEMA)

    The NEMA framework is a multinational, multidisciplinary cyber-infrastructure project for music information processing that builds upon and extends the music information retrieval research being conducted by IMIRSEL in UIUC. NEMA brings together collective projects and the associated tools of multiple world leaders in the domains of MIR, Computational Musicology (CM) and e-humanities research. The NEMA team aims to create an open and extensible web-service based resource framework that facilitates the integration of music data and analytic/evaluative tools which can be used by the global MIR and CM research and education communities on a basis independent of time or location.

  • Structural Analysis of Large Amounts of Music Information (SALAMI)

    SALAMI will analyse 23,000 hours of digitised music to build a resource for musicologists, based on the music’s underlying structure. It will use thousands of supercomputing hours, donated by the National Center for Supercomputing Applications (NCSA), and draw on a bewildering range of music from the Internet Archive –from A Capella to Zydeco, Appalachia to Zambia, and Medieval to Post-Modern.