jMIR is an open-source software suite implemented in Java for use in music information retrieval (MIR) research. It can be used to study music in the form of audio recordings, symbolic encodings and lyrical transcriptions, and can also mine cultural information from the Internet. It also includes tools for managing and profiling large music collections and for checking audio for production errors. jMIR includes software for extracting features, applying machine learning algorithms, applying heuristic error error checkers, mining metadata and analyzing metadata.

The primary emphasis of jMIR is on providing software for general research in automatic music classification and similarity analysis. The main goals of the project are as follows:

In order to meet these goals, all aspects of jMIR are open source and distributed free under a GNU General Public License. The software is well-documented and include GUIs in order to increase general usability. A special emphasis has been placed on software architectures that facilitate extensibility for those technically inclined users who wish to modify or add to the software.

More details are available in the academic publications on jMIR's components. The manuals and other documentation for each jMIR component also provide helpful documentation.

Each of the components comprising the jMIR software suite may be used entirely separately or as an integrated whole. The components communicate with each other using files in either ACE XML, Weka ARFF or CSV formats. The components are as follows:

Data Mining and Machine Learning

Feature Extraction

Education and Audio Production

Data and Metadata


Graphical Overview of Music Classification Tasks and Corresponding (Original) jMIR Components:

-top of page-