Music Information Retrieval

Abstract

Welcome friends and colleagues to the 2 nd Annual International Symposium on Music Information Retrieval -ISMIR 2001.Following on the heels of last year's groundbreaking inaugural conference, we're convening with colleagues this year at the beautiful campus of Indiana University, Bloomington. We hope the information exchange fostered by this conference will facilitate innovation and enhance collaboration in this dynamic area of research. This year's program is rich in content and variety. We are honored to have David Cope present this year's keynote address. The presentations by our four invited speakers, Roger Dannenberg, Jef Raskin, Youngmoo Kim, and Adam Lindsay provide added depth and breadth to an already dynamic and diverse program.This document includes the texts of the accepted papers along with the extended abstracts of the invited talks and poster presentations. All are also available on the ISMIR 2001Web site at: http:// ismir2001.indiana.edu/ As with last year, we were very encouraged by the number and quality of submissions. Response to our Call for Papers was remarkable. Selecting the twenty papers for presentation (out of 40 submissions) and the eighteen posters for exhibition was no easy task. I'd like to personally thank all those that gave of their time to help review submissions.Unending appreciation and thanks must be extended to the Program Committee: David Bainbridge (Program Chair), Gerry Bernbom, Donald Byrd, Tim Crawford, Jon Dunn, and Michael Fingerhut.Additionally I'd like to thank Dr. Stephen Griffin of the National Science Foundation, for helping us secure the foundational funding that made this symposium possible. Dr. Radha Nandkumar of the National Center for Supercomputing Applications, University of Illinois at Urbana-Champaign, must also be thanked for providing financial support to help us augment our student stipend program.Finally, several departments and individuals at our host institution, Indiana University Bloomington, deserve thanks. A great deal of the planning that went into this conference was done by Diane Jung, Charles Rondot, David Taylor, and Les Teach, of the Communications and Planning Office under the Office of the Vice President for Information Technology and CIO, and by Tawana Green and the staff of the IU Conference Bureau. Their assistance is much appreciated. In addition, the Indiana University School of Music generously supplied an extraordinary instrument, a fortepiano, for the mini-recital at the Mathers Museum. Sincerely ABSTRACTWe present a measure of the similarity of the long-term structure of musical pieces. The system deals with raw polyphonic data. Through unsupervised learning, we generate an abstract representation of music -the "texture score". This "texture score" can be matched to other similar scores using a generalized edit distance, in order to assess structural similarity. We notably apply this algorithm to the retrieval of different interpretations of the same song within a music database. MOTIVATIONMotivation for this system is our be...

Music questions in social Q&A: an analysis of Yahoo! Answers

“…One of these tools is social question and answer (social Q&A) sites. While research on music information retrieval has mainly addressed the automatic extraction of features from music files to make these features available for retrieval (Burgoyne et al, 2016, Schedl et al, 2014, social Q&A sites provide an opportunity for studying what information real users seek and what information they specify to retrieve it. Such studies are necessary to understand the match between real information needs and the features that can be automatically extracted from music files and to investigate the role of social Q&A in music information seeking.…”

Smart Musical Instruments: Vision, Design Principles, and Future Directions

“…As shown in Section I, SMIs lie in an emerging field positioned at the intersection of new interfaces for musical expression [44], Internet of Things [13], music information retrieval [17], networked music performance [92], and technology-mediated audience participation [39]. Based on the examples of existing musical instruments termed as ''smart'' (as reviewed in Section II-A) as well as the author's observations, this section aims to propose a vision for the future smart instruments, by presenting a definition for them, describing their underlying technological architecture, and proposing scenarios illustrating the new capabilities they offer.…”

“…Another set of authors have investigated computational methods for the extraction of information from the sound of musical instruments, within the fields of music information retrieval (MIR) [17] and semantic audio [99]. More often such methods are applied offline, especially by analyzing large datasets of audio files [5], while some authors have used real-time feature extraction for performance purposes [15], [43], [45], [74], especially employing machine learning techniques [29], [91].…”

The Digital Music Lab

“…[Pugin 2015;Duval et al 2015;Ng et al 2014]. Digital datasets in music are smaller than in some other domains, and according to [Burgoyne et al 2016], of the openly accessible music datasets only the Million Song Dataset 5 qualifies as "truly 'big"' with 280GB of feature data extracted from 1 million audio tracks. However, the quantity of music data is growing and even the smaller data sets available now are big in the sense that the traditional musicological method, where the researcher closely inspects every work, is no longer applicable.…”