M2K Alpha 1.1 MIREX Edition

M2K represents the music-specific set of D2K modules designed to create a Virtual Research Lab (VRL) for MIR/MDL development, prototyping and evaluation.

See:
Description

Packages

org.imirsel.m2k.evaluation	Provides modules for the reading in of data files used in in MIREX05 frameworks, and evaluators that operate over those data files.
org.imirsel.m2k.filters	Provides modules for applying filters and filter banks on input data.
org.imirsel.m2k.io	Provides modules for system input/output and signal generation.
org.imirsel.m2k.math	Provides classes for performing arithmatic.
org.imirsel.m2k.modelling	Provides modules for applying models to input data (such as Gaussians, Gaussian Mixture Models, Hidden Markov Models).
org.imirsel.m2k.modelling.linearDiscriminantAnalysis
org.imirsel.m2k.my_modules	Provides a package to contain any modules implemented by M2K users and a template for the implementation of those modules.
org.imirsel.m2k.testing	Provides modules for testing other M2K modules.
org.imirsel.m2k.transforms	Provides modules for computing transformations on input data(such as FFT, DCT).
org.imirsel.m2k.util	Contains utility modules (manipulating arrays, Signal, splitting input for cross validation, etc.).
org.imirsel.m2k.vis	Provides modules for visualizing results.

M2K represents the music-specific set of D2K modules designed to create a Virtual Research Lab (VRL) for MIR/MDL development, prototyping and evaluation. M2K provides the framework for the MIREX (Music Information Retrieval Evaluation eXchange) contest, an annual MIR evaluation.

The IMIRSEL (International Music Information Retrieval Systems Evaluation Laboratory) project provides an unprecedented platform for evaluating Music Information Retrieval (MIR) and Music Digital Library (MDL) techniques, by bringing together large corpora and significant computational resources with the necessary rights management and technical infrastructure to support a variety of MIR/MDL research areas. The standardized research collection being deployed represents a large and diverse corpus of musical examples, which we are hosting in our secure environment for use in evaluating MIR/MDL algorithms. Grid services and National Center for Supercomputing Application's (NCSA) D2K (Data-to-Knowledge) machine learning environment provide a powerful, high performance, and secure framework for designing, optimising, and executing complex MIR/MDL evaluation applications. IMIRSEL provides a community resource for researchers who would otherwise not be able to afford the content rights and computational resources to carry out large-scale MIR/MDL evaluations. J. Stephen Downie, Assistant Professor at the Graduate School of Library and Information Science (GSLIS), University of Illinois at Urbana-Champaign (UIUC), is director of IMIRSEL and is the project principal investigator (PI).

M2K (Music-to-Knowledge) is a key element of the IMIRSEL project. M2K represents the music-specific set of D2K modules designed to create a Virtual Research Lab (VRL) for MIR/MDL development, prototyping and evaluation. The VRLs will be used by MIR/MDL researchers so they can participate in future MIREX (Music Information Retrieval Evaluation eXchange) contests.

D2K, together with a subsidary set of modules called, T2K (Text-to-Knowledge), provide the basic foundation upon which M2K is being developed. D2K/T2K are the result of a ongoing research and development project of the Automated Learning Group (ALG) at NCSA. ALG is headed by Prof. Michael Welge who is also an IMIRSEL project co-PI.

For more information visit the M2K Page