A toolkit for computational music research and evaluation. M2K is module set for the National Center for Supercomputing Application's (NCSA) Data-to-Knowledge (D2K) machine learning environment.

D2K "is a rapid, flexible data mining and machine learning system that integrates analytical data mining methods for prediction, discovery, and deviation detection, with data and information visualization tools. It offers a visual programming environment that allows users to connect programming modules together to build data mining applications and supplies a core set of modules, application templates, and a standard API for software component development.

All D2K components are written in Java for maximum flexibility and portability". Development in the D2K environment has allowed us to rapidly prototype, distribute and parrallelise computationally expensive MIR applications.

M2K is made up of modules that perform specific tasks related to Music Information Retrieval (MIR). Modules are included to perform various types of DSP, data preparation and output (including plotting tools), Machine Learning, Integration of code external to M2K (calling binaries) and evaluation of performance on MIR tasks. The visual interface provided in D2K allows MIR researchers to rapidly prototype and evaluate new MIR algorithms, without having to 're-implement' basic services. M2K also provides the framework for the MIREX (Music Information Retrieval Evaluation eXchange) contest, an annual MIR evaluation.

M2K has been developed in partnership with the International Music Information Retrieval Systems Evaluation Laboratory (IMIRSEL) and the Sun Microsystems Laboratories' "Search Inside the Music" project. Go to the main project pages and M2K (and other required installs) downloads.

Research Team

Mr. Kris West