NEMA@McGill

Overview of NEMA

The Networked Environment for Music Analysis (NEMA) project is a multinational and multidisciplinary cyber-infrastructure project for music information processing that builds upon and extends the music information retrieval research being conducted by the International Music Information Retrieval Systems Evaluation Laboratory (IMIRSEL) at the University of Illinois at Urbana-Champaign (UIUC). NEMA brings together the collective projects and the associated tools of six world leaders in the domains of music information retrieval (MIR), computational musicology (CM) and e-humanities research. The NEMA team aims to create an open and extensible web services-based resource framework that facilitates the integration of music data and analytic/evaluative tools that can be used by the global MIR and CM research and education communities on a basis independent of time or location. To help achieve this goal, the NEMA team will be working co-operatively with the UIUC-based and Mellon-funded Software Environment for the Advancement of Scholarly Research (SEASR) project to exploit SEASR’s expertise and technologies in the domains of data mining and web services-based resource framework development.

NEMA is being funded through a generous grant from the Scholarly Communications program of the Andrew W. Mellon Foundation.

People Involved in NEMA at McGill University

Current NEMA Development Emphasis at McGill University

Overview of ACE

ACE is part of the jMIR software project. 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 both audio and symbolic formats as well as mine cultural information from the web and manage music collections. jMIR includes software for extracting features, applying machine learning algorithms and analyzing metadata.
ACE (Autonomous Classification Engine) is a meta-learning software package for selecting, optimizing and applying machine learning algorithms to music research. Given a set of feature vectors, ACE experiments with a variety of classifiers, classifier parameters, classifier ensemble architectures and dimensionality reduction techniques in order to arrive at a good configuration for the problem at hand. This can be important, as different algorithms can be appropriate for different problems and types of data. ACE is designed to increase classification success rates, facilitate the application of powerful machine learning technology for users of all technical levels and provide a framework for experimenting with new algorithms.

Overview of ACE XML

NOTE: Development updates relating to ACE XML are posted on the ACE XML development page.

ACE XML is a set of file formats developed to enable communication between the various jMIR software components. These file formats have been designed to be very flexible and expressive, and are intended to eventually be adopted beyond the limited scope of jMIR as a multi-purpose standardized format by the music information retrieval (MIR) research community.

The current lack of a standardized general-purpose format for storing specialized MIR-related information such as class ontologies, feature values and ground truth labels that meets the specific needs of MIR research has resulted in the emergence of the Weka ARFF format as a de facto in MIR. Although ARFF and Weka in general are powerful tools, they have not been designed with the specific needs of music in mind, and thus have a number of important limitations when applied to MIR research. ACE XML is therefore designed as a more expressive and flexible alternative.

UPDATE 1: A key element of our current research focus is the improvement and extension of the new ACE ZIP file formats. The four basic ACE XML file format types (expressing feature values, feature definitions, instance labels and taxonomical class structures) can now be automatically packaged into a single ZIP file. This means that those users who want to package related files for a given project into a single file can do so, and those users who wish to maintain the advantages of keeping the file types distinct and separate can still do so. The ACE API and command line tool also now includes functionality for saving and processing ACE ZIP files.

UPDATE 2: ACE's GUI is now partially finished. Users can browse and edit ACE XML files and data more conveniently, without needing a text editor. A pre-Alpha version is now available for internal NEMA use, but it is still very much in the initial development stages, and has a number of unresolved bugs and features that are still in the process of being implemented.

UPDATE 3: A draft version of Cory McKay's dissertation chapter on ACE XML is now available. It includes significant background information, discussion of the design decisions behind ACE XML and extensive documentation of the file formats, including sample files.

UPDATE 4: Section 8.11 of the chapter mentioned above also proposes an overhauled version of the ACE XML file formats called ACE XML 2.0. The changes to the formats are primarily motivated by the needs of the NEMA project. The ACE XML 2.0 file formats are presented simply as prototypes for general discussion and amendment by the NEMA community, and the original ACE XML 1.1 formats remain the standard ACE XML format at the moment.

UPDATE 5: Updates to the ACE XML 2.0 formats have been made. Updated sample files are available on the ACE XML development page, and the dissertation chapter has also been updated.

UPDATE 6 (April 19 2009): ACE XML 2.0 sample file formats further updated and dissertation chapter draft updated appropriately. Details on the ACE XML development page.

UPDATE 7 (April 27 2009): ACE XML 2.0 sample file formats further updated and dissertation chapter draft updated appropriately. Details on the ACE XML development page.

UPDATE 8 (May 2 2009): ACE XML development page significantly revised and ACE XML 2.0 Specification Document posted.

UPDATE 9 (June 19 2009): Presented jMIR and ACE XML at JCDL.

UPDATE 10 (August 17 2009): Presented jMIR demo at ICMC.

UPDATE 11 (October 1 2009): Published release version of ACE 2.0 on SourceForge.

UPDATE 12 (October 27 and October 28): Presented ACE XML and ACE 2.0 posters at ISMIR.

Other Preliminary Milestones Completed

Currently Being Worked On

Publications Relating to ACE and ACE XML

McKay, C., J. A. Burgoyne, and I. Fujinaga. 2009. jMIR and ACE XML: Tools for performing and sharing research in automatic music classification. Presented at the ACM/IEEE Joint Conference on Digital Libraries Workshop on Integrating Digital Library Content with Computational Tools and Services, University of Texas, Austin, USA. 19 June 2009.

McKay, C., J. A. Burgoyne, J. Thompson, and I. Fujinaga. 2009. Using ACE XML 2.0 to store and share feature, instance and class data for musical classification. Proceedings of the International Society for Music Information Retrieval Conference. 303–8.

McKay, C., and I. Fujinaga. 2009. jMIR: Tools for automatic music classification. Proceedings of the International Computer Music Conference.

Thompson, J., C. McKay, J. A. Burgoyne, and I. Fujinaga. 2009. Additions and improvements to the ACE 2.0 music classifier. Proceedings of the International Society for Music Information Retrieval Conference. 435–40.

McKay, C., and I. Fujinaga. 2008. Combining Features Extracted From Audio, Symbolic and Cultural Sources. Proceedings of the International Conference on Music Information Retrieval. 597–602.

McKay, C., and I. Fujinaga. 2007. Style-independent computer-assisted exploratory analysis of large music collections. Journal of Interdisciplinary Music Studies 1 (1): 63–85.

McKay, C., R. Fiebrink, D. McEnnis, B. Li, and I. Fujinaga. 2005. ACE: A framework for optimizing music classification. Proceedings of the International Conference on Music Information Retrieval. 42–9.

McKay, C., D. McEnnis, R. Fiebrink, and I. Fujinaga. 2005. ACE: A general-purpose classification ensemble optimization framework. Proceedings of the International Computer Music Conference. 161–4.

Sinyor, E., C. McKay, R. Fiebrink, D. McEnnis, and I. Fujinaga. 2005. Beatbox classification using ACE. Proceedings of the International Conference on Music Information Retrieval. 672–5.

Publications Relating to Other jMIR Components

McEnnis, D., C. McKay, and I. Fujinaga. 2006. jAudio: Additions and improvements. Proceedings of the International Conference on Music Information Retrieval. 385–6.

McEnnis, D., C. McKay, and I. Fujinaga. 2006. Overview of OMEN. Proceedings of the International Conference on Music Information Retrieval. 7–12.

McEnnis, D., C. McKay, I. Fujinaga, and P. Depalle. 2005. jAudio: A feature extraction library. Proceedings of the International Conference on Music Information Retrieval. 600–3.

McKay, C., and I. Fujinaga. 2007. jWebMiner: A web-based feature extractor. Accepted for publication at the 2007 International Conference on Music Information Retrieval.

McKay, C., and I. Fujinaga. 2007. Style-independent computer-assisted exploratory analysis of large music collections. Journal of Interdisciplinary Music Studies 1 (1): 63–85.

McKay, C., D. McEnnis and I. Fujinaga. 2006. A large publicly accessible prototype audio database for music research. Proceedings of the International Conference on Music Information Retrieval. 160–3.

McKay, C., and I. Fujinaga. 2006. jSymbolic: A feature extractor for MIDI files. Proceedings of the International Computer Music Conference. 302–5.

McKay, C., and I. Fujinaga. 2005. Automatic music classification and the importance of instrument identification. Proceedings of the Conference on Interdisciplinary Musicology. CD-ROM.

McKay, C., and I. Fujinaga. 2005. The Bodhidharma system and the results of the MIREX 2005 symbolic genre classification contest. Presented at the International Conference on Music Information Retrieval.

McKay, C. 2004. Automatic genre classification as a study of the viability of high-level features for music classification. Proceedings of the International Computer Music Conference. 367–70.

McKay, C. 2004. Automatic genre classification of MIDI recordings. M.A. Thesis. McGill University, Canada.

McKay, C. and I. Fujinaga. 2004. Automatic genre classification using large high-level musical feature sets. Proceedings of the International Conference on Music Information Retrieval. 525–30.

Questions and Comments

cory.mckay@mail.mcgill.ca

DOWNLOAD jMIR FROM SOURCEFORGE

-top of page-