This paper outlines the findings-to-date of a project to assist in the efforts being made to establish a TREC-like evaluation paradigm within the Music Information Retrieval (MIR) research community. The findings

Music Information Retrieval (MIR) is an interdisciplinary research area that has grown out of the need to manage burgeoning collections of music in digital form. Its diverse disciplinary communities have yet to articulate a common research agenda or agree on methodological principles and metrics of success. In order for MIR to succeed, researchers need to work with real user communities and develop research resources such as reference music collections, so that the wide variety of techniques being developed in MIR can be meaningfully compared with one another. Out of these efforts, a common MIR practice can emerge.

The planning for a music information retrieval testbed must include consideration of the potential users for a music collection and their information needs. In particular, we must have a clear idea of what an MIR system’s potential users are looking for, how they describe the object of their search, and how they approach the task of fulfilling their information needs. 1.

Music Information Retrieval (MIR) is an interdisciplinary research area that has grown out of the need to manage burgeoning collections of music in digital form. Its diverse disciplinary communities, exemplified by the recently established ISMIR conference series, have yet to articulate a common research agenda or agree on methodological principles and metrics of success. In order for MIR to succeed, researchers need to work with real user communities and develop research resources such as reference music collections, so that the wide variety of techniques being developed in MIR can be meaningfully compared with one another. Out of these efforts, a common MIR practice can emerge.

Music Information Retrieval (MIR) is a multidisciplinary research endeavor that strives to develop innovative content-based searching schemes, novel interfaces, and evolving networked delivery mechanisms in an effort to make the world’s vast store of music accessible to all. Some teams are developing ‘‘Query-by-Singing’’ and ‘‘Query-by-Humming’’ systems that allow users to interact with their respective music search engines via queries that are sung or hummed into a microphone (e.g., Birmingham et al. 2001; Haus and Pollastri 2001). ‘‘Queryby-Note’’ systems are also being developed wherein searchers construct queries consisting of pitch and/or rhythm information (e.g., Pickens 2000; Doraisamy and Rüger 2002). Input methods for Queryby-Note systems include symbolic interfaces as well as both physical (MIDI) and virtual (Javabased) keyboards. Some teams are working on ‘‘Query-by-Example’’ systems that take prerecorded music in the form of CD or MP3 tracks as their query input (e.g., Haitsma and Kalker 2002; Harb and Chen 2003). The development of comprehensive music recommendation and distribution systems is a growing research area (e.g., Logan 2002; Pauws and Eggen 2002). The automatic generation of playlists for use in personal music systems, based on a wide variety of user-defined criteria, is the goal of this branch of MIR research. Other groups are investigating the creation of music analysis systems to assist those in the musicology and music theory communities (e.g., Barthélemy

PerlHumdrum is an alternative toolkit for working with large numbers of Humdrum scores. While based on the original Humdrum toolkit, it is a completely new, self-contained implementation that can serve as a replacement, and may be a better choice for some computing systems. PerlHumdrum is fully object-oriented, is designed to easily facilitate analysis and processing of multiple humdrum files, and to answer common musicological questions across entire sets, collections of music, or even the entire output of single or multiple composers. Several extended capabilities that are not available in the original toolkit are also provided, such as translation of MIDI scores to Humdrum, provisions for constructing graphs, a graphical user interface for non-programmers, and the ability to generate complete scores or partial musical examples as standard musical notation using PerlLilypond. These tools are intended primarily for use by music theorists, computational musicologists, and Music Information Retrieval (MIR) researchers. 1

Symbolic music information retrieval is one of the most underrepresented areas in the field of MIR. Here, symbolic music means common practice music notation–the musician readable format. In this paper we introduce a novel rule-based symbolic music retrieval mechanism. The Scripting system–ENP-Script–is augmented with MIR functionality. It allows us to perform sophisticated retrieval operations on symbolic musical scores prepared with the help of the music notation system ENP. We will also give a special attention to visualization of the query results. All the statistical queries, such as histograms, are visualized with the help of common music notation where appropriate. N-grams and more complex queries–the ones dealing with voice leading, for example–

In this paper we present the EASY (Electro-Acoustic muSic analYsis) Toolbox software system for assisting electro-acoustic music analysis. The primary aims of the system are to present perceptually relevant features and audio descriptors via visual designs to gain more insight into electro-acoustic music works and provide easy-touse “click-and-go ” software interface paradigms for practical use of the system by non-experts and experts alike. The development of the EASY system exploits MIR techniques with particular emphasis on the electroacoustic music repertoire – musical pieces that concentrate on timbral dimensions rather than traditional elements such as pitch, melody, harmony, and rhythm. The project was mainly inspired by the lack of software tools available for aiding electro-acoustic music analysis. The system’s frameworks, feature analysis algorithms, along with the initial analyses of pieces are presented here.