Showing papers by "J. Stephen Downie published in 2003"
26 Oct 2003
TL;DR: A Wizard of Oz approach to system evaluation, combined with a grounded theory analysis of 502 real-world music queries posted to Google Answers, addresses this pivotal question of how users of music information retrieval systems express their needs.
Abstract: How do users of music information retrieval (MIR) systems express their needs? Using a Wizard of Oz approach to system evaluation, combined with a grounded theory analysis of 502 real-world music queries posted to Google Answers, this paper addresses this pivotal question.
84 citations
Proceedings Article•
26 Oct 2003TL;DR: Recommendations include the creation of data-rich query records that are both grounded in real-world requirements and neutral with respect to retrieval technique(s) being examined; adoption, and subsequent validation, of a “reasonable person” approach to “relevance” assessment.
Abstract: 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 and recommendations are based upon expert opinion garnered from members of the Information Retrieval (IR), Music Digital Library (MDL) and MIR communities with regard to the construction and implementation of scientifically valid evaluation frameworks. Proposed recommendations include the creation of data-rich query records that are both grounded in real-world requirements and neutral with respect to retrieval technique(s) being examined; adoption, and subsequent validation, of a “reasonable person” approach to “relevance” assessment; and, the development of a secure, yet accessible, research environment that allows researchers to remotely access the large-scale testbed collection.
53 citations
TL;DR: 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.
Abstract: 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.
41 citations
Proceedings Article•
01 Jan 2003
TL;DR: A Wizard of Oz approach to system evaluation, combined with a grounded theory analysis of 502 real-world music queries posted to Google Answers, addresses this pivotal question of how users of music information retrieval systems express their needs.
Abstract: How do users of music information retrieval (MIR) systems express their needs? Using a Wizard of Oz approach to system evaluation, combined with a grounded theory analysis of 502 real-world music queries posted to Google Answers, this paper addresses this pivotal question.
8 citations
01 Sep 2003
TL;DR: Music Information Retrieval and Music Digital Library research brings together computer scientists, audio engineers, librarians, musicologists, educators and business executives in a common effort to provide robust mechanisms for organizing, storing and accessing the world’s everincreasing volume of music.
Abstract: Music Information Retrieval (MIR) and Music Digital Library (MDL) are two interrelated, multidisciplinary research areas with a growing community of involved parties. MIR/MDL research brings together computer scientists, audio engineers, librarians, musicologists, educators and business executives in a common effort to provide robust mechanisms for organizing, storing and accessing the world’s everincreasing volume of music. Newcomers to the world of MIR/MDL are invited to read Downie [8], Futrelle and Downie [10], and Byrd and Crawford [3] for overviews of issues currently being examined by MIR/MDL researchers.
4 citations
26 Oct 2003
TL;DR: The University of Chicago Library has digitized a collection of 19 century music scores, generated programmatically from the scanned images and human-created descriptive and structural metadata, encoded as METS objects, and delivered using the Greenstone Digital Library software.
Abstract: The University of Chicago Library has digitized a collection of 19 century music scores. The online collection is generated programmatically from the scanned images and human-created descriptive and structural metadata, encoded as METS objects, and delivered using the Greenstone Digital Library software. Use statistics are analyzed and possible future directions for the collection are discussed.
4 citations
28 Jul 2003
TL;DR: This poster reports upon the ongoing efforts being made to establish TREC-like and other comprehensive evaluation paradigms within the Music IR (MIR) and Music Digital Library (MDL) research communities.
Abstract: This poster reports upon the ongoing efforts being made to establish TREC-like and other comprehensive evaluation paradigms within the Music IR (MIR) and Music Digital Library (MDL) research communities The proposed research tasks are based upon expert opinion garnered from members of the Information Retrieval (IR), MDL and MIR communities with regard to the construction and implementation of scientifically valid evaluation frameworks
3 citations
Proceedings Article•
01 Jan 2003
2 citations