@InProceedings{Achankunju2018,

author = {Achankunju, Sanu Pulimootil},

booktitle = {1st International Workshop on Reading Music Systems},

title = {Music Search Engine from Noisy {OMR} Data},

year = {2018},

address = {Paris, France},

editor = {Calvo-Zaragoza, Jorge and Haji{\v{c}} jr., Jan and Pacha, Alexander},

pages = {23--24},

file = {:pdfs/2018 - Music Search Engine from Noisy OMR Data.pdf:PDF},

url = {https://sites.google.com/view/worms2018/proceedings},

}

@InProceedings{Adamska2015,

author = {Adamska, Julia and Piecuch, Mateusz and Podg{\'o}rski, Mateusz and Walkiewicz, Piotr and Lukasik, Ewa},

booktitle = {Computer Information Systems and Industrial Management},

title = {Mobile System for Optical Music Recognition and Music Sound Generation},

year = {2015},

address = {Cham},

editor = {Saeed, Khalid and Homenda, Wladyslaw},

pages = {571--582},

publisher = {Springer International Publishing},

abstract = {The paper presents a mobile system for generating a melody based on a photo of a musical score. The client-server architecture was applied. The client role is designated to a mobile application responsible for taking a photo of a score, sending it to the server for further processing and playing mp3 file received from the server. The server role is to recognize notes from the image, generate mp3 file and send it to the client application. The key element of the system is the program realizing the algorithm of notes recognition. It is based on the decision trees and characteristics of the individual symbols extracted from the image. The system is implemented in the Windows Phone 8 framework and uses a cloud operating system Microsoft Azure. It enables easy archivization of photos, recognized notes in the Music XML format and generated mp3 files. An easy transition to other mobile operating systems is possible as well as processing multiple music collections scans.},

affiliation = {Institute of Computing Science, Poznan University of Technology, Poznań, Poland},

author_keywords = {Mobile applications; Omr; Optical music recognition; Windows phone},

doi = {10.1007/978-3-319-24369-6_48},

file = {:pdfs/2015 - Mobile System for Optical Music Recognition.pdf:PDF},

isbn = {978-3-319-24369-6},

}

@TechReport{AlfaroContreras2020,

author = {Alfaro-Contreras, Mar{\'{i}}a and Calvo-Zaragoza, Jorge and I{\~{n}}esta, Jos{\'{e}} M.},

institution = {Departamento de Lenguajes y Sistemas Informáticos, Universidad de Alicante, Spain},

title = {Reconocimiento hol{\'{i}}stico de partituras musicales},

year = {2020},

file = {:pdfs/2020 - Reconocimiento Holistico De Partituras Musicales.pdf:PDF},

language = {Spanish},

url = {https://rua.ua.es/dspace/bitstream/10045/108270/1/Reconocimiento_holistico_de_partituras_musicales.pdf},

}

@InProceedings{AlfaroContreras2021,

author = {Alfaro-Contreras, Mar\'{i}a and Valero-Mas, Jose J. and I{\~{n}}esta, Jos{\'e} Manuel},

booktitle = {Proceedings of the 3rd International Workshop on Reading Music Systems},

title = {Neural architectures for exploiting the components of Agnostic Notation in Optical Music Recognition},

year = {2021},

address = {Alicante, Spain},

editor = {Calvo-Zaragoza, Jorge and Pacha, Alexander},

pages = {33--37},

file = {:pdfs/2021 - Neural Architectures for Exploiting the Components of Agnostic Notation in Optical Music Recognition.pdf:PDF},

url = {https://sites.google.com/view/worms2021/proceedings},

}

@InProceedings{AlfaroContreras2023,

author = {Alfaro-Contreras, Mar\'{i}a},

booktitle = {Proceedings of the 5th International Workshop on Reading Music Systems},

title = {Few-Shot Music Symbol Classification via Self-Supervised Learning and Nearest Neighbor},

year = {2023},

address = {Milan, Italy},

editor = {Calvo-Zaragoza, Jorge and Pacha, Alexander and Shatri, Elona},

pages = {39--43},

doi = {10.48550/arXiv.2311.04091},

file = {:pdfs/2023 - Few Shot Music Symbol Classification Via Self Supervised Learning and Nearest Neighbor.pdf:PDF},

url = {https://sites.google.com/view/worms2023/proceedings},

}

@Article{Alirezazadeh2014,

author = {Alirezazadeh, Fatemeh and Ahmadzadeh, Mohammad Reza},

journal = {Journal of Advanced Computer Science \& Technology},

title = {Effective staff line detection, restoration and removal approach for different quality of scanned handwritten music sheets},

year = {2014},

number = {2},

pages = {136--142},

volume = {3},

doi = {10.14419/jacst.v3i2.3196},

file = {:pdfs/2014 - Effective staff line detection, restoration and removal approach for different quality of scanned handwritte music sheets.pdf:PDF},

publisher = {Science Publishing Corporation},

}

@InProceedings{Andronico1982,

author = {Alfio Andronico and Alberto Ciampa},

booktitle = {International Computer Music Conference},

title = {On Automatic Pattern Recognition and Acquisition of Printed Music},

year = {1982},

address = {Venice, Italy},

publisher = {Michigan Publishing},

bibsource = {dblp computer science bibliography, https://dblp.org},

biburl = {https://dblp.org/rec/bib/conf/icmc/AndronicoC82},

file = {:pdfs/1982 - On Automatic Pattern Recognition and Acquisition of Printed Music.pdf:PDF},

url = {http://hdl.handle.net/2027/spo.bbp2372.1982.024},

}

@InProceedings{Anquetil2000,

author = {Anquetil, {\'E}ric and Co{\"u}asnon, Bertrand and Dambreville, Fr{\'e}d{\'e}ric},

booktitle = {Graphics Recognition Recent Advances},

title = {A Symbol Classifier Able to Reject Wrong Shapes for Document Recognition Systems},

year = {2000},

address = {Berlin, Heidelberg},

editor = {Chhabra, Atul K. and Dori, Dov},

pages = {209--218},

publisher = {Springer Berlin Heidelberg},

abstract = {We propose in this paper a new framework to develop a transparent classifier able to deal with reject notions. The generated classifier can be characterized by a strong reliability without loosing good properties in generalization. We show on a musical scores recognition system that this classifier is very well suited to develop a complete document recognition system. Indeed this classifier allows them firstly to extract known symbols in a document (text for example) and secondly to validate segmentation hypotheses. Tests had been successfully performed on musical and digit symbols databases.},

file = {:pdfs/2000 - A Symbol Classifier Able to Reject Wrong Shapes for Document Recognition Systems.pdf:PDF},

isbn = {978-3-540-40953-3},

url = {https://link.springer.com/chapter/10.1007/3-540-40953-X_17},

}

@InProceedings{Anstice1996,

author = {Anstice, Jamie and Bell, Tim and Cockburn, Andy and Setchell, Martin},

booktitle = {6th Australian Conference on Computer-Human Interaction},

title = {The design of a pen-based musical input system},

year = {1996},

pages = {260--267},

abstract = {Computerising the task of music editing can avoid a considerable amount of tedious work for musicians, particularly for tasks such as key transposition, part extraction, and layout. However the task of getting the music onto the computer can still be time consuming and is usually done with the help of bulky equipment. This paper reports on the design of a pen-based input system that uses easily-learned gestures to facilitate fast input, particularly if the system must be portable. The design is based on observations of musicians writing music by hand, and an analysis of the symbols in samples of music. A preliminary evaluation of the system is presented, and the speed is compared with the alternatives of handwriting, synthesiser keyboard input, and optical music recognition. Evaluations suggest that the gesture-based system could be approximately three times as fast as other methods of music data entry reported in the literature.},

doi = {10.1109/OZCHI.1996.560019},

file = {:pdfs/1996 - The Design of a Pen Based Musical Input System.pdf:PDF},

keywords = {light pens;pen-based musical input system;music editing;key transposition;part extraction;music layout;time consuming;gesture interface;symbols;handwriting;synthesiser keyboard input;optical music recognition;music data entry;Writing;Keyboards;Proposals;Mice;Liquid crystal displays;Computer science;Handwriting recognition;Music information retrieval;Content based retrieval;Portable computers},

}

@InProceedings{Armand1993,

author = {Armand, Jean-Pierre},

booktitle = {2nd International Conference on Document Analysis and Recognition},

title = {Musical score recognition: A hierarchical and recursive approach},

year = {1993},

pages = {906--909},

abstract = {Musical scores for live music show specific characteristics: large format, orchestral score, bad quality of (photo) copies. Moreover such music is generally handwritten. The author addresses the music recognition problem for such scores, and show a dedicated filtering that has been developed, both for segmentation and correction of copy defects. Recognition process involves geometrical and topographical parameters evaluation. The whole process (filtering recognition) is recursively applied on images and sub-images, in a knowledge-based way.<<ETX>>},

doi = {10.1109/ICDAR.1993.395590},

file = {:pdfs/1993 - Musical Score Recognition_ a Hierarchical and Recursive Approach.pdf:PDF},

keywords = {image recognition;music;geometrical evaluation;musical score recognition;hierarchical;recursive;live music show specific characteristics;large format;orchestral score;handwritten;music recognition;dedicated filtering;segmentation;correction;copy defects;topographical parameters evaluation;filtering;recognition;images;sub-images;knowledge-based;Filtering;Image segmentation;Music;Head;Image recognition;Digital filters;Morphology;EMP radiation effects;Electronic mail;Classification algorithms},

}

@Misc{Audiveris,

author = {Bitteur, Herv{\'{e}}},

howpublished = {\url{https://github.com/audiveris}},

title = {Audiveris},

year = {2004},

url = {https://github.com/audiveris},

}

@InProceedings{Baba2012,

author = {Baba, Tetsuaki and Kikukawa, Yuya and Yoshiike, Toshiki and Suzuki, Tatsuhiko and Shoji, Rika and Kushiyama, Kumiko and Aoki, Makoto},

booktitle = {ACM SIGGRAPH 2012 Emerging Technologies},

title = {Gocen: A Handwritten Notational Interface for Musical Performance and Learning Music},

year = {2012},

address = {New York, USA},

pages = {9--9},

publisher = {ACM},

acmid = {2343465},

doi = {10.1145/2343456.2343465},

file = {:pdfs/2012 - Gocen - A Handwritten Notational Interface for Musical Performance and Learning Music.pdf:PDF},

isbn = {978-1-4503-1680-4},

}

@Article{Bacon1988,

author = {Bacon, Richard A. and Carter, Nicholas Paul},

journal = {Physics Bulletin},

title = {Recognising music automatically},

year = {1988},

number = {7},

pages = {265},

volume = {39},

abstract = {Recognising characters typed in at a keyboard is a familiar task to most computers and one at which they excel, except that they (usually) insist on recognising what we have typed, rather than what we meant to type. A number of programs now on the market, however, go rather beyond merely recognising keystrokes on a keyboard, to actually recognising printed words on paper.},

file = {:pdfs/1988 - Recognising Music Automatically.pdf:PDF},

url = {http://stacks.iop.org/0031-9112/39/i=7/a=013},

}

@Misc{Bainbridge1991,

author = {Bainbridge, David},

title = {Preliminary experiments in musical score recognition},

year = {1991},

address = {Edinburgh, Scotland},

comment = {B.Sc. Thesis},

school = {University of Edinburgh},

}

@TechReport{Bainbridge1994,

author = {Bainbridge, David},

institution = {University of Canterbury},

title = {A complete optical music recognition system: Looking to the future},

year = {1994},

file = {:pdfs/1994 - A Complete Optical Music Recognition System - Looking to the Future.pdf:PDF},

url = {https://ir.canterbury.ac.nz/handle/10092/14874},

}

@TechReport{Bainbridge1994a,

author = {Bainbridge, David},

institution = {Department of Computer Science, University of Canterbury},

title = {Optical music recognition: Progress report 1},

year = {1994},

file = {:pdfs/1994 - Optical Music Recognition - Progress Report 1.pdf:PDF},

url = {http://hdl.handle.net/10092/9670},

}

@Article{Bainbridge1996,

author = {Bainbridge, David and Bell, Tim},

journal = {Australian Computer Science Communications},

title = {An extensible optical music recognition system},

year = {1996},

pages = {308--317},

volume = {18},

booktitle = {The Nineteenth Australasian computer science conference},

comment = {Last seen 07.04.2017},

file = {:pdfs/1997 - An extensible Optical Music Recognition system.pdf:PDF},

publisher = {University of Canterbury},

url = {http://www.cs.waikato.ac.nz/~davidb/publications/acsc96/final.html},

}

@InProceedings{Bainbridge1997,

author = {Bainbridge, David and Bell, Tim},

booktitle = {6th International Conference on Image Processing and its Applications},

title = {Dealing with Superimposed Objects in Optical Music Recognition},

year = {1997},

number = {443},

pages = {756--760},

abstract = {Optical music recognition ({OMR}) involves identifying musical symbols on a scanned sheet of music, and interpreting them so that the music can either be played by the computer, or put into a music editor. Applications include providing an automatic accompaniment, transposing or extracting parts for individual instruments, and performing an automated musicological analysis of the music. A key problem with music recognition, compared with character recognition, is that symbols very often overlap on the page. The most significant form of this problem is that the symbols are superimposed on a five-line staff. Although the staff provides valuable positional information, it creates ambiguity because it is difficult to determine whether a pixel would be black or white if the staff line was not there. The other main difference between music recognition and character recognition is the set of permissible symbols. In text, the alphabet size is fixed. Conversely, in music notation there is no standard "alphabet" of shapes, with composers inventing new notation where necessary, and music for particular instruments using specialised notation where appropriate. The focus of this paper is on techniques we have developed to deal with superimposed objects (6 Refs.) recognition},

doi = {10.1049/cp:19970997},

file = {:pdfs/1997 - Dealing with Superimposed Objects in Optical Music Recognition.pdf:PDF},

isbn = {0 85296 692 X},

issn = {0537-9989},

keywords = {m, optical music recognition, superimposed objects, to classify},

}

@PhdThesis{Bainbridge1997a,

author = {Bainbridge, David},

school = {University of Canterbury},

title = {Extensible optical music recognition},

year = {1997},

file = {:pdfs/1997 - Extensible Optical Music Recognition.pdf:PDF},

pages = {112},

url = {http://hdl.handle.net/10092/9420},

}

@InCollection{Bainbridge1997b,

author = {Bainbridge, David and Carter, Nicholas Paul},

booktitle = {Handbook of Character Recognition and Document Image Analysis},

publisher = {World Scientific},

title = {Automatic reading of music notation},

year = {1997},

address = {Singapore},

editor = {Bunke, H. and Wang, P.},

pages = {583--603},

abstract = {The aim of Optical Music Recognition (OMR) is to convert optically scanned pages of music into a machine-readable format. In this tutorial level discussion of the topic, an historical background of work is presented, followed by a detailed explanation of the four key stages to an OMR system: stave line identification, musical object location, symbol identification, and musical understanding. The chapter also shows how recent work has addressed the issues of touching and fragmented objects—objectives that must be solved in a practical OMR system. The report concludes by discussing remaining problems, including measuring accuracy.},

doi = {10.1142/9789812830968_0022},

file = {:pdfs/1997 - Automatic Reading of Music Notation.pdf:PDF},

}

@InProceedings{Bainbridge1998,

author = {Bainbridge, David and Inglis, Stuart},

booktitle = {Data Compression Conference},

title = {Musical image compression},

year = {1998},

pages = {209--218},

abstract = {Optical music recognition aims to convert the vast repositories of sheet music in the world into an on-line digital format. In the near future it will be possible to assimilate music into digital libraries and users will be able to perform searches based on a sung melody in addition to typical text-based searching. An important requirement for such a system is the ability to reproduce the original score as accurately as possible. Due to the huge amount of sheet music available, the efficient storage of musical images is an important topic of study. This paper investigates whether the "knowledge" extracted from the optical music recognition (OMR) process can be exploited to gain higher compression than the JBIG international standard for bi-level image compression. We present a hybrid approach where the primitive shapes of music extracted by the optical music recognition process-note heads, note stems, staff lines and so forth-are fed into a graphical symbol based compression scheme originally designed for images containing mainly printed text. Using this hybrid approach the average compression rate for a single page is improved by 3.5% over JBIG. When multiple pages with similar typography are processed in sequence, the file size is decreased by 4-8%. The relevant background to both optical music recognition and textual image compression is presented. Experiments performed on 66 test images are described, outlining the combinations of parameters that were examined to give the best results.},

doi = {10.1109/DCC.1998.672149},

file = {:pdfs/1998 - Musical Image Compression.pdf:PDF},

issn = {1068-0314},

keywords = {music;optical character recognition;image coding;data compression;musical image compression;optical music recognition;sheet music;on-line digital format;digital libraries;text-based searching;music score;musical image storage;JBIG international standard;bi-level image compression;hybrid approach;primitive shapes;note heads;note stems;staff lines;graphical symbol based compression;printed text;average compression rate;file size;textual image compression;experiments;Image coding;Image recognition;Image storage;Image converters;Software libraries;Ordinary magnetoresistance;Shape;Text recognition;Head;Optical design},

}

@InProceedings{Bainbridge1999,

author = {Bainbridge, David and Wijaya, K.},

booktitle = {7th International Conference on Image Processing and its Applications},

title = {Bulk processing of optically scanned music},

year = {1999},

pages = {474--478},

publisher = {Institution of Engineering and Technology},

abstract = {For many years now optical music recognition (OMR) has been advocated as the leading methodology for transferring the vast repositories of music notation from paper to digital database. Other techniques exist for acquiring music on-line; however, these methods require operators with musical and computer skills. The notion, therefore, of an entirely automated process through OMR is highly attractive. It has been an active area of research since its inception in 1966 (Pruslin), and even though there has been the development of many systems with impressively high accuracy rates it is surprising to note that there is little evidence of large collections being processed with the technology-work by Carter (1994) and Bainbridge and Carter (1997) being the only known notable exception. This paper outlines some of the insights gained, and algorithms implemented, through the practical experience of converting collections in excess of 400 pages. In doing so, the work demonstrates that there are additional factors not currently considered by other research centres that are necessary for OMR to reach its full potential.},

affiliation = {Waikato Univ., Hamilton},

doi = {10.1049/cp:19990367},

keywords = {OMR;optical music recognition;optically scanned music;bulk processing;music notation;digital database;},

url = {http://digital-library.theiet.org/content/conferences/10.1049/cp_19990367},

}

@Article{Bainbridge2001,

author = {Bainbridge, David and Bell, Tim},

journal = {Computers and the Humanities},

title = {The Challenge of Optical Music Recognition},

year = {2001},

issn = {1572-8412},

number = {2},

pages = {95--121},

volume = {35},

abstract = {This article describes the challenges posed by optical musicrecognition

-- a topic in computer science that aims to convert scannedpages

of music into an on-line format. First, the problem is described;then

a generalised framework for software is presented that emphasises

keystages that must be solved: staff line identification, musical

objectlocation, musical feature classification, and musical semantics.

Next,significant research projects in the area are reviewed, showing

how eachfits the generalised framework. The article concludes by

discussingperhaps the most open question in the field: how to compare

the accuracy and success of rival systems, highlighting certain steps

thathelp ease the task.},

doi = {10.1023/A:1002485918032},

file = {:pdfs/2001 - The challenge of optical music recognition.pdf:PDF},

isbn = {0010-4817},

keywords = {document image analysis, musical data acquisition, optical music recognition, pattern, to classify},

}

@InProceedings{Bainbridge2001a,

author = {Bainbridge, David and Bernbom, Gerry and Davidson, Mary Wallace and Dillon, Andrew P. and Dovey, Matthey and Dunn, Jon W. and Fingerhut, Michael and Fujinaga, Ichiro and Isaacson, Eric J.},

booktitle = {1st ACM/IEEE-CS Joint Conference on Digital Libraries},

title = {Digital Music Libraries --- Research and Development},

year = {2001},

address = {Roanoke, Virginia, USA},

pages = {446--448},

doi = {10.1145/379437.379765},

file = {:pdfs/2001 - Digital Music Libraries Research and Development.pdf:PDF},

}

@Article{Bainbridge2003,

author = {Bainbridge, David and Bell, Tim},

journal = {Software: Practice and Experience},

title = {A music notation construction engine for optical music recognition},

year = {2003},

issn = {1097-024X},

number = {2},

pages = {173--200},

volume = {33},

abstract = {Optical music recognition (OMR) systems are used to convert music scanned from paper into a format suitable for playing or editing on a computer. These systems generally have two phases: recognizing the graphical symbols (such as note-heads and lines) and determining the musical meaning and relationships of the symbols (such as the pitch and rhythm of the notes). In this paper we explore the second phase and give a two-step approach that admits an economical representation of the parsing rules for the system. The approach is flexible and allows the system to be extended to new notations with little effort—the current system can parse common music notation, Sacred Harp notation and plainsong. It is based on a string grammar and a customizable graph that specifies relationships between musical objects. We observe that this graph can be related to printing as well as recognizing music notation, bringing the opportunity for cross-fertilization between the two areas of research. Copyright © 2003 John Wiley & Sons, Ltd.},

doi = {10.1002/spe.502},

file = {:pdfs/2003 - A music notation construction engine for optical music recognition - Bainbridge and Bell.pdf:PDF},

keywords = {optical music recognition, music notation construction, definite clause grammars, graph traversal},

publisher = {John Wiley \& Sons, Ltd.},

}

@InProceedings{Bainbridge2006,

author = {Bainbridge, David and Bell, Tim},

booktitle = {7th International Conference on Music Information Retrieval},

title = {Identifying music documents in a collection of images},

year = {2006},

address = {Victoria, Canada},

pages = {47--52},

abstract = {Digital libraries and search engines are now well-equipped to find images of documents based on queries. Many images of music scores are now available, often mixed up with textual documents and images. For example, using the Google “images” search feature, a search for “Beethoven” will return a number of scores and manuscripts as well as pictures of the composer. In this paper we report on an investigation into methods to mechanically determine if a particular document is indeed a score, so that the user can specify that only musical scores should be returned. The goal is to find a minimal set of features that can be used as a quick test that will be applied to large numbers of documents.

A variety of filters were considered, and two promising ones (run-length ratios and Hough transform) were evaluated. We found that a method based around run-lengths in vertical scans (RL) that out-performs a comparable algorithm using the Hough transform (HT). On a test set of 1030 images, RL achieved recall and precision of 97.8% and 88.4% respectively while HT achieved 97.8% and 73.5%. In terms of processor time, RL was more than five times as fast as HT.},

file = {:pdfs/2006 - Identifying Music Documents in a Collection of Images.pdf:PDF},

url = {http://hdl.handle.net/10092/141},

}

@InProceedings{Bainbridge2014,

author = {Bainbridge, David and Hu, Xiao and Downie, J. Stephen},

booktitle = {1st International Workshop on Digital Libraries for Musicology},

title = {A Musical Progression with Greenstone: How Music Content Analysis and Linked Data is Helping Redefine the Boundaries to a Music Digital Library},

year = {2014},

publisher = {Association for Computing Machinery},

abstract = {Despite the recasting of the web's technical capabilities through Web 2.0, conventional digital library software architectures-from which many of our leading Music Digital Libraries (MDLs) are formed-result in digital resources that are, surprisingly, disconnected from other online sources of information, and embody a "read-only" mindset. Leveraging from Music Information Retrieval (MIR) techniques and Linked Open Data (LOD), in this paper we demonstrate a new form of music digital library that encompasses management, discovery, delivery, and analysis of the musical content it contains. Utilizing open source tools such as Greenstone, audioDB, Meandre, and Apache Jena we present a series of transformations to a musical digital library sourced from audio files that steadily increases the level of support provided to the user for musicological study. While the seed for this work was motivated by better supporting musicologists in a digital library, the developed software architecture alters the boundaries to what is conventionally thought of as a digital library- and in doing so challenges core assumptions made in mainstream digital library software design. Copyright 2014 ACM.},

affiliation = {University of Waikato, Hamilton, New Zealand; University of Hong Kong, Hong Kong; University of Illinois, Urbana-Champaign, IL, United States},

doi = {10.1145/2660168.2660170},

file = {:pdfs/2014 - A Musical Progression with Greenstone.pdf:PDF},

isbn = {9781450330022},

keywords = {Audio acoustics; Open source software; Software architecture; Software design, Digital music libraries; Embedded workflow; Linked open data (LOD); Music content analysis; Music digital libraries; Music information retrieval; Musicology analysis; Technical capabilities, Digital libraries},

}

@InProceedings{Balke2015,

author = {Balke, Stefan and Achankunju, Sanu Pulimootil and M{\"{u}}ller, Meinard},

booktitle = {International Conference on Acoustics, Speech and Signal Processing},

title = {Matching Musical Themes Based on Noisy {OCR} and {OMR} Input},

year = {2015},

pages = {703--707},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {In the year 1948, Barlow and Morgenstern published the book 'A Dictionary of Musical Themes', which contains 9803 important musical themes from the Western classical music literature. In this paper, we deal with the problem of automatically matching these themes to other digitally available sources. To this end, we introduce a processing pipeline that automatically extracts from the scanned pages of the printed book textual metadata using Optical Character Recognition (OCR) as well as symbolic note information using Optical Music Recognition (OMR). Due to the poor printing quality of the book, the OCR and OMR results are quite noisy containing numerous extraction errors. As one main contribution, we adjust alignment techniques for matching musical themes based on the OCR and OMR input. In particular, we show how the matching quality can be substantially improved by fusing the OCR- and OMR-based matching results. Finally, we report on our experiments within the challenging Barlow and Morgenstern scenario, which also indicates the potential of our techniques when considering other sources of musical themes such as digital music archives and the world wide web.},

affiliation = {International Audio Laboratories Erlangen, Friedrich-Alexander-Universität (FAU), Germany},

doi = {10.1109/ICASSP.2015.7178060},

file = {:pdfs/2015 - Matching Musical Themes Based on Noisy OCR and OMR Input.pdf:PDF},

isbn = {9781467369978},

issn = {1520-6149},

keywords = {others},

}

@Article{Balke2018,

author = {Balke, Stefan and Dittmar, Christian and Abe{\ss}er, Jakob and Frieler, Klaus and Pfleiderer, Martin and M{\"{u}}ller, Meinard},

journal = {Frontiers in Digital Humanities},

title = {Bridging the Gap: Enriching YouTube Videos with Jazz Music Annotations},

year = {2018},

issn = {2297-2668},

pages = {1--11},

volume = {5},

abstract = {Web services allow permanent access to music from all over the world. Especially in the case of web services with user-supplied content, e.g., YouTube(TM), the available metadata is often incomplete or erroneous. On the other hand, a vast amount of high-quality and musically relevant metadata has been annotated in research areas such as Music Information Retrieval (MIR). Although they have great potential, these musical annotations are ofter inaccessible to users outside the academic world. With our contribution, we want to bridge this gap by enriching publicly available multimedia content with musical annotations available in research corpora, while maintaining easy access to the underlying data. Our web-based tools offer researchers and music lovers novel possibilities to interact with and navigate through the content. In this paper, we consider a research corpus called the Weimar Jazz Database (WJD) as an illustrating example scenario. The WJD contains various annotations related to famous jazz solos. First, we establish a link between the WJD annotations and corresponding YouTube videos employing existing retrieval techniques. With these techniques, we were able to identify 988 corresponding YouTube videos for 329 solos out of 456 solos contained in the WJD. We then embed the retrieved videos in a recently developed web-based platform and enrich the videos with solo transcriptions that are part of the WJD. Furthermore, we integrate publicly available data resources from the Semantic Web in order to extend the presented information, for example, with a detailed discography or artists-related information. Our contribution illustrates the potential of modern web-based technologies for the digital humanities, and novel ways for improving access and interaction with digitized multimedia content.},

doi = {10.3389/fdigh.2018.00001},

file = {:pdfs/2018 - Bridging the Gap - Enrichting YouTube Videos with Jazz Music Annotations.pdf:PDF},

}

@InProceedings{Baro2016,

author = {Bar{\'{o}}, Arnau and Riba, Pau and Forn{\'{e}}s, Alicia},

booktitle = {15th International Conference on Frontiers in Handwriting Recognition},

title = {Towards the recognition of compound music notes in handwritten music scores},

year = {2016},

pages = {465--470},

publisher = {Institute of Electrical and Electronics Engineers Inc.},

abstract = {The recognition of handwritten music scores still remains an open

problem. The existing approaches can only deal with very simple handwritten

scores mainly because of the variability in the handwriting style

and the variability in the composition of groups of music notes (i.e.

compound music notes). In this work we focus on this second problem

and propose a method based on perceptual grouping for the recognition

of compound music notes. Our method has been tested using several

handwritten music scores of the CVC-MUSCIMA database and compared

with a commercial Optical Music Recognition (OMR) software. Given

that our method is learning-free, the obtained results are promising.},

affiliation = {Computer Vision Center, Dept. of Computer Science, Universitat Autònoma de Barcelona, Bellaterra, Catalonia, Spain},

author_keywords = {Hand-drawn symbol recognition; Handwritten music scores; Optical music recognition; Perceptual grouping},

bibsource = {dblp computer science bibliography, http://dblp.org},

biburl = {http://dblp.uni-trier.de/rec/bib/conf/icfhr/BaroRF16},

doi = {10.1109/ICFHR.2016.0092},

file = {:pdfs/2016 - Towards the recognition of compound music notes in handwritten music scores.pdf:PDF},

isbn = {9781509009817},

issn = {2167-6445},

keywords = {Pattern recognition; Software testing, Hand-drawn symbols; Handwriting Styles; Music notes; Music scores; Optical music recognition; Perceptual grouping, Character recognition},

}

@InProceedings{Baro2017,

author = {Bar{\'o}, Arnau and Riba, Pau and Calvo-Zaragoza, Jorge and Forn{\'e}s, Alicia},

booktitle = {14th International Conference on Document Analysis and Recognition},

title = {Optical Music Recognition by Recurrent Neural Networks},

year = {2017},

address = {Kyoto, Japan},

organization = {IEEE},

pages = {25--26},

doi = {10.1109/ICDAR.2017.260},

file = {:pdfs/2017 - Optical Music Recognition by Recurrent Neural Networks.pdf:PDF},

issn = {2379-2140},

}

@InProceedings{Baro2018,

author = {Bar{\'{o}}, Arnau and Riba, Pau and Forn{\'{e}}s, Alicia},

booktitle = {1st International Workshop on Reading Music Systems},

title = {A Starting Point for Handwritten Music Recognition},

year = {2018},

address = {Paris, France},

editor = {Calvo-Zaragoza, Jorge and Haji{\v{c}} jr., Jan and Pacha, Alexander},

pages = {5--6},

file = {:pdfs/2018 - A Starting Point for Handwritten Music Recognition.pdf:PDF},

url = {https://sites.google.com/view/worms2018/proceedings},

}

@Article{Baro2019,

author = {Bar{\'{o}}, Arnau and Riba, Pau and Calvo-Zaragoza, Jorge and Forn{\'{e}}s, Alicia},

journal = {Pattern Recognition Letters},

title = {From Optical Music Recognition to Handwritten Music Recognition: A baseline},

year = {2019},

issn = {0167-8655},

pages = {1--8},

volume = {123},

abstract = {Optical Music Recognition (OMR) is the branch of document image analysis that aims to convert images of musical scores into a computer-readable format. Despite decades of research, the recognition of handwritten music scores, concretely the Western notation, is still an open problem, and the few existing works only focus on a specific stage of OMR. In this work, we propose a full Handwritten Music Recognition (HMR) system based on Convolutional Recurrent Neural Networks, data augmentation and transfer learning, that can serve as a baseline for the research community.},

doi = {https://doi.org/10.1016/j.patrec.2019.02.029},

file = {:pdfs/2019 - From Optical Music Recognition to Handwritten Music Recognition_ a Baseline.pdf:PDF},

keywords = {Optical music recognition, Handwritten music recognition, Document image analysis and recognition, Deep neural networks, LSTM},

url = {http://www.sciencedirect.com/science/article/pii/S0167865518303386},

}

@InProceedings{Baro2021,

author = {Bar\'{o}, Arnau and Badal, Carles and Torras, Pau and Forn\'{e}s, Alicia},

booktitle = {Proceedings of the 3rd International Workshop on Reading Music Systems},

title = {Handwritten Historical Music Recognition through Sequence-to-Sequence with Attention Mechanism},

year = {2021},

address = {Alicante, Spain},

editor = {Calvo-Zaragoza, Jorge and Pacha, Alexander},

pages = {55--59},

file = {:pdfs/2021 - Handwritten Historical Music Recognition through Sequence to Sequence with Attention Mechanism.pdf:PDF},

url = {https://sites.google.com/view/worms2021/proceedings},

}

@MastersThesis{Baro-Mas2017,

author = {Bar{\'{o}}-Mas, Arnau},

school = {Universitat Aut{\`{o}}noma de Barcelona},

title = {Optical Music Recognition by Long Short-Term Memory Recurrent Neural Networks},

year = {2017},

file = {:pdfs/2017 - Optical Music Recognition by Long Short-Term memory Recurrent Neural Networks.pdf:PDF},

pages = {1--20},

url = {http://www.cvc.uab.es/people/afornes/students/Master_ABaro2017.pdf},

}

@InProceedings{Barton2002,

author = {Barton, Louis W. G.},

booktitle = {2nd International Conference on Web Delivering of Music},

title = {The {NEUMES} Project: digital transcription of medieval chant manuscripts},

year = {2002},

pages = {211--218},

abstract = {This paper introduces the NEUMES Project from a top-down perspective. The purpose of the project is to design a software infrastructure for digital transcription of medieval chant manuscripts, such that transcriptions can be interoperable across many types of applications programs. Existing software for modern music does not provide an effective solution. A distributed library of chant document resources for the Web is proposed, to encompass photographic images, transcriptions, and searchable databases of manuscript descriptions. The NEUMES encoding scheme for chant transcription is presented, with NeumesXML serving as a 'wrapper' for transmission, storage, and editorial markup of transcription data. A scenario of use is given and future directions for the project are briefly discussed.},

doi = {10.1109/WDM.2002.1176213},

file = {:pdfs/2002 - The NEUMES Project_ Digital Transcription of Medieval Chant Manuscripts.pdf:PDF},

keywords = {music;hypermedia markup languages;data structures;history;open systems;Internet;NEUMES Project;software infrastructure;digital transcription;medieval chant manuscripts;interoperability;distributed library;chant document resources;Web;photographic images;searchable databases;encoding scheme;NeumesXML;editorial markup;storage;transmission;Writing;Books;Libraries;Inspection;Encoding;Uncertainty;Shape;Scholarships;Lighting},

}

@InProceedings{Barton2005,

author = {Barton, Louis W. G. and Caldwell, John A. and Jeavons, Peter G.},

booktitle = {5th ACM/IEEE-CS Joint Conference on Digital Libraries},

title = {E-library of Medieval Chant Manuscript Transcriptions},

year = {2005},

address = {Denver, CO, USA},

pages = {320--329},

publisher = {ACM},

acmid = {1065458},

doi = {10.1145/1065385.1065458},

file = {:pdfs/2005 - E Library of Medieval Chant Manuscript Transcriptions.pdf:PDF},

isbn = {1-58113-876-8},

keywords = {XML, chant, comparison, data representation, digital libraries, medieval manuscripts, musical notation, search, transcription},

}

@InCollection{Baumann1992,

author = {Baumann, Stephan and Dengel, Andreas},

booktitle = {Advances in Structural and Syntactic Pattern Recognition},

publisher = {World Scientific},

title = {Transforming Printed Piano Music into {MIDI}},

year = {1992},

pages = {363--372},

abstract = {This paper decribes a recognition system for transforming printed piano music into the international standard MIDI for acoustic output generation. Because of the system is adapted for processing musical scores, it follows a top-down strategy in order to take advantage of the hierarchical structuring. Applying a decision tree classifier and various musical rules, the system comes up with a recognition rate of 80 to 100\% depending on the musical complexity of the input. The resulting symbolic representation in terms of so called MIDI-EVENTs can be easily understood by musical devices such as synthesizers, expanders, or keyboards.},

doi = {10.1142/9789812797919_0030},

file = {:pdfs/1992 - Transforming Printed Piano Music into MIDI.pdf:PDF},

}

@TechReport{Baumann1993,

author = {Baumann, Stephan},

institution = {Deutsches Forschungszentrum für Künstliche Intelligenz GmbH},

title = {Document recognition of printed scores and transformation into {MIDI}},

year = {1993},

doi = {10.22028/D291-24925},

file = {:pdfs/1993 - Document Recognition of Printed Scores and Transformation into MIDI.pdf:PDF},

}

@InProceedings{Baumann1995,

author = {Baumann, Stephan},

booktitle = {3rd International Conference on Document Analysis and Recognition},

title = {A Simplified Attributed Graph Grammar for High-Level Music Recognition},

year = {1995},

pages = {1080--1083},

publisher = {IEEE},

doi = {10.1109/ICDAR.1995.602096},

file = {:pdfs/1995 - A Simplified Attributed Graph Grammar for High-Level Music Recognition.pdf:PDF},

isbn = {0-8186-7128-9},

}

@InProceedings{Baumann1995a,

author = {Baumann, Stephan and Tombre, Karl},

booktitle = {Document Analysis Systems},

title = {Report of the line drawing and music recognition working group},

year = {1995},

editor = {Spitz, A. Lawrence and Dengel, Andreas},

pages = {1080--1083},

doi = {10.1142/9789812797933},

}

@InProceedings{Bellini2001,

author = {Bellini, Pierfrancesco and Bruno, Ivan and Nesi, Paolo},

booktitle = {1st International Conference on WEB Delivering of Music},

title = {Optical music sheet segmentation},

year = {2001},

pages = {183--190},

publisher = {Institute of Electrical {\&} Electronics Engineers ({IEEE})},

abstract = {The optical music recognition problem has been addressed in several ways, obtaining suitable results only when simple music constructs are processed. The most critical phase of the optical music recognition process is the first analysis of the image sheet. The first analysis consists of segmenting the acquired sheet into smaller parts which may be processed to recognize the basic symbols. The segmentation module of the O³ {MR} system (Object Oriented Optical Music Recognition) system is presented. The proposed approach is based on the adoption of projections for the extraction of basic symbols that constitute a graphic element of the music notation. A set of examples is also included.},

doi = {10.1109/wdm.2001.990175},

file = {:pdfs/2001 - Optical Music Sheet Segmentation.pdf:PDF},

groups = {recognition},

isbn = {0769512844},

}

@InCollection{Bellini2004,

author = {Bellini, Pierfrancesco and Bruno, Ivan and Nesi, Paolo},

booktitle = {Visual Perception of Music Notation: On-Line and Off Line Recognition},

publisher = {IGI Global},

title = {An Off-Line Optical Music Sheet Recognition},

year = {2004},

pages = {40--77},

doi = {10.4018/978-1-59140-298-5.ch002},

file = {:pdfs/2004 - An Off-line Optical Music Sheet Recognition.pdf:PDF},

groups = {interpretation},

}

@Article{Bellini2007,

author = {Bellini, Pierfrancesco and Bruno, Ivan and Nesi, Paolo},

journal = {Computer Music Journal},

title = {Assessing Optical Music Recognition Tools},

year = {2007},

number = {1},

pages = {68--93},

volume = {31},

doi = {10.1162/comj.2007.31.1.68},

file = {:pdfs/2007 - Assessing Optical Music Recognition Tools.pdf:PDF},

groups = {evaluation},

publisher = {MIT Press},

}

@InCollection{Bellini2008,

author = {Bellini, Pierfrancesco and Bruno, Ivan and Nesi, Paolo},

booktitle = {Interactive Multimedia Music Technologies},

publisher = {IGI Global},

title = {Optical Music Recognition: Architecture and Algorithms},

year = {2008},

address = {Hershey, PA, USA},

editor = {Ng, Kia and Nesi, Paolo},

pages = {80--110},

abstract = {Optical music recognition is a key problem for coding western music sheets in the digital world. This problem has been addressed in several manners obtaining suitable results only when simple music constructs are processed. To this end, several different strategies have been followed, to pass from the simple music sheet image to a complete and consistent representation of music notation symbols (symbolic music notation or representation). Typically, image processing, pattern recognition and symbolic reconstruction are the technologies that have to be considered and applied in several manners the architecture of the so called OMR (Optical Music Recognition) systems. In this chapter, the O3MR (Object Oriented Optical Music Recognition) system is presented. It allows producing from the image of a music sheet the symbolic representation and save it in XML format (WEDELMUSIC XML and MUSICXML). The algorithms used in this process are those of the image processing, image segmentation, neural network pattern recognition, and symbolic reconstruction and reasoning. Most of the solutions can be applied in other field of image understanding. The development of the O3MR solution with all its algorithms has been partially supported by the European Commission, in the IMUTUS Research and Development project, while the related music notation editor has been partially funded by the research and development WEDELMUSIC project of the European Commission. The paper also includes a methodology for the assessment of other OMR systems. The set of metrics proposed has been used to assess the quality of results produce by the O3MR with respect the best OMR on market.},

file = {:pdfs/2008 - Optical Music Recognition - Architecture and Algorithms - Sample.pdf:PDF},

issn = {9781599041506},

journal = {Interactive Multimedia Music Technologies},

refid = {24555},

url = {http://services.igi-global.com/resolvedoi/resolve.aspx?doi=10.4018/978-1-59904-150-6.ch005},

}

@InProceedings{Beran1999,

author = {Beran, Tom{\'a}{\v{s}} and Macek, Tom{\'a}{\v{s}}},

booktitle = {Machine Learning and Data Mining in Pattern Recognition},

title = {Recognition of Printed Music Score},

year = {1999},

editor = {Perner, Petra and Petrou, Maria},

pages = {174--179},

publisher = {Springer Berlin Heidelberg},

abstract = {This article describes our implementation of the Optical Music Recognition System (OMR). The system implemented in our project is based on the binary neural network ADAM. ADAM has been used for recognition of music symbols. Preprocessing was implemented by conventional techniques. We decomposed the OMR process into several phases. The results of these phases are summarized.},

doi = {10.1007/3-540-48097-8_14},

file = {:pdfs/1999 - Recognition of Printed Music Score.pdf:PDF},

isbn = {978-3-540-48097-6},

}

@InProceedings{Blostein1990,

author = {Blostein, Dorothea and Haken, Lippold},

booktitle = {10th International Conference on Pattern Recognition},

title = {Template matching for rhythmic analysis of music keyboard input},

year = {1990},

pages = {767--770},

abstract = {A system that recognizes common rhythmic patterns through template matching is described. The use of template matching gives the user the unusual ability to modify the set of templates used for analysis. This modification effects a tradeoff between the temporal accuracy required of the input and the complexity of the recognizable rhythm patterns that happen to be common in a particular piece of music. The evolving implementation of this algorithm has received heavy use over a six-year period and has proven itself as a practical and reliable input method for fast music transcription. It is concluded that templates demonstrably provide the necessary temporal context for accurate rhythm recognition.<<ETX>>},

doi = {10.1109/ICPR.1990.118213},

file = {:pdfs/1990 - Template Matching for Rhythmic Analysis of Music Keyboard Input.pdf:PDF},

keywords = {acoustic signal processing;computerised pattern recognition;computerised signal processing;music;rhythmic pattern recognition;music keyboard input;template matching;music transcription;Multiple signal classification;Keyboards;Timing;Pattern recognition;Music;Rhythm;Computer errors;Councils;Laboratories;Information science},

}

@Article{Blostein1991,

author = {Blostein, Dorothea and Haken, Lippold},

journal = {Communications of the ACM},

title = {Justification of Printed Music},

year = {1991},

issn = {0001-0782},

number = {3},

pages = {88--99},

volume = {34},

acmid = {102874},

address = {New York, NY, USA},

doi = {10.1145/102868.102874},

file = {:pdfs/1991 - Justification of Printed Music.pdf:PDF},

issue_date = {March 1991},

publisher = {ACM},

}

@InCollection{Blostein1992,

author = {Blostein, Dorothea and Baird, Henry S.},

booktitle = {Structured Document Image Analysis},

publisher = {Springer Berlin Heidelberg},

title = {A Critical Survey of Music Image Analysis},

year = {1992},

isbn = {978-3-642-77281-8},

pages = {405--434},

abstract = {The research literature concerning the automatic analysis of images of printed and handwritten music notation, for the period 1966 through 1990, is surveyed and critically examined.},

doi = {10.1007/978-3-642-77281-8_19},

file = {:pdfs/1992 - A Critical Survey of Music Image Analysis.pdf:PDF},

}

@InCollection{Blostein1992a,

author = {Blostein, Dorothea and Carter, Nicholas Paul},

booktitle = {Structured Document Image Analysis},

publisher = {Springer Berlin Heidelberg},

title = {Recognition of Music Notation: SSPR'90 Working Group Report},

year = {1992},

isbn = {978-3-642-77281-8},

pages = {573--574},

abstract = {This report summarizes the discussions of the Working Group on the Recognition of Music Notation, of the IAPR 1990 Workshop on Syntactic and Structural Pattern Recognition, Murray Hill, NJ, 13--15 June 1990. The participants were: D. Blostein, N. Carter, R. Haralick, T. Itagaki, H. Kato, H. Nishida, and R. Siromoney. The discussion was moderated by Nicholas Carter and recorded by Dorothea Blostein.},

doi = {10.1007/978-3-642-77281-8_32},

file = {:pdfs/1992 - Recognition of Music Notation_ SSPR'90 Working Group Report.pdf:PDF},

url = {https://doi.org/10.1007/978-3-642-77281-8_32},

}

@Article{Blostein1999,

author = {Blostein, Dorothea and Haken, Lippold},

journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},

title = {Using diagram generation software to improve diagram recognition: a case study of music notation},

year = {1999},

issn = {0162-8828},

number = {11},

pages = {1121--1136},

volume = {21},

abstract = {Diagrams are widely used in society to transmit information such as circuit designs, music, mathematical formulae, architectural plans, and molecular structure. Computers must process diagrams both as images (marks on paper) and as information. A diagram recognizer translates from image to information and a diagram generator translates from information to image. Current technology for diagram generation is ahead of the technology for diagram recognition. Diagram generators have extensive knowledge of notational conventions which relate to readability and aesthetics, whereas current diagram recognizers focus on the hard constraints of the notation. To create a recognizer capable of exploiting layout information, it is expedient to reuse the expertise in existing diagram generators. In particular, we discuss the use of Lime (our editor and generator for music notation) to proofread and correct the raw output of MIDIScan (a third-party commercial recognizer for music notation). Over the past several years, this combination of software has been distributed to thousands of users.},

doi = {10.1109/34.809106},

file = {:pdfs/1999 - Using Diagram Generation Software to Improve Diagram Recognition_ a Case Study of Music Notation.pdf:PDF},

keywords = {music;diagrams;document image processing;image recognition;diagram generation software;diagram recognition;music notation;notational conventions;readability;aesthetics;layout information;Lime;proofreading;correction;raw output;MIDIScan;Computer aided software engineering;Multiple signal classification;Image recognition;Mathematics;Computer errors;Error correction;Character recognition;Software systems;Circuit synthesis;Image analysis},

}

@InProceedings{Bonnici2018,

author = {Bonnici, Alexandra and Abela, Julian and Zammit, Nicholas and Azzopardi, George},

booktitle = {ACM Symposium on Document Engineering},

title = {Automatic Ornament Localisation, Recognition and Expression from Music Sheets},

year = {2018},

address = {Halifax, NS, Canada},

pages = {25:1--25:11},

publisher = {ACM},

acmid = {3209536},

doi = {10.1145/3209280.3209536},

file = {:pdfs/2018 - Automatic Ornament Localisation, Recognition and Expression from Music Sheets.pdf:PDF},

isbn = {978-1-4503-5769-2},

url = {http://doi.acm.org/10.1145/3209280.3209536},

}

@InProceedings{Bountouridis2017,

author = {Bountouridis, Dimitrios and Wiering, Frans and Brown, Dan and Veltkamp, Remco C.},

booktitle = {Computational Intelligence in Music, Sound, Art and Design},

title = {Towards Polyphony Reconstruction Using Multidimensional Multiple Sequence Alignment},

year = {2017},

address = {Cham},

editor = {Correia, Jo{\~a}o and Ciesielski, Vic and Liapis, Antonios},

pages = {33--48},

publisher = {Springer International Publishing},

abstract = {The digitization of printed music scores through the process of optical music recognition is imperfect. In polyphonic scores, with two or more simultaneous voices, errors of duration or position can lead to badly aligned and inharmonious digital transcriptions. We adapt biological sequence analysis tools as a post-processing step to correct the alignment of voices. Our multiple sequence alignment approach works on multiple musical dimensions and we investigate the contribution of each dimension to the correct alignment. Structural information, such musical phrase boundaries, is of major importance; therefore, we propose the use of the popular bioinformatics aligner Mafft which can incorporate such information while being robust to temporal noise. Our experiments show that a harmony-aware Mafft outperforms sophisticated, multidimensional alignment approaches and can achieve near-perfect polyphony reconstruction.},

doi = {10.1007/978-3-319-55750-2_3},

file = {:pdfs/2017 - Towards polyhony reconstruction using multidimensional multiple sequence alignment.pdf:PDF},

isbn = {978-3-319-55750-2},

}

@InProceedings{Bruder2003,

author = {Bruder, Ilvio and Finger, Andreas and Heuer, Andreas and Ignatova, Temenushka},

booktitle = {Digital Libraries: Technology and Management of Indigenous Knowledge for Global Access},

title = {Towards a Digital Document Archive for Historical Handwritten Music Scores},

year = {2003},

address = {Berlin, Heidelberg},

editor = {Sembok, Tengku Mohd Tengku and Zaman, Halimah Badioze and Chen, Hsinchun and Urs, Shalini R. and Myaeng, Sung-Hyon},

pages = {411--414},

publisher = {Springer Berlin Heidelberg},

abstract = {Contemporary digital libraries and archives of music scores focus mainly on providing efficient storage and access methods for their data. However, digital archives of historical music scores can enable musicologists not only to easily store and access research material, but also to derive new knowledge from existing data. In this paper we present the first steps in building a digital archive of historical music scores from the 17th and 18th century. Along with the architectural and accessibility aspects of the system, we describe an integrated approach for classification and identification of the scribes of music scores.},

doi = {10.1007/978-3-540-24863-0_41},

file = {:pdfs/2003 - Towards a Digital Document Archive for Historical Handwritten Music Scores.pdf:PDF},

isbn = {978-3-540-24863-0},

}

@InProceedings{Bugge2011,

author = {Bugge, Esben Paul and Juncher, Kim Lundsteen and Mathiasen, Brian Soborg and Simonsen, Jakob Grue},

booktitle = {12th International Society for Music Information Retrieval Conference},

title = {Using Sequence Alignment and Voting To Improve Optical Music Recognition From Multiple Recognizers},

year = {2011},

pages = {405--410},

abstract = {Digitalizing sheet music using Optical Music Recognition ({OMR}) is error-prone, especially when using noisy images created from scanned prints. Inspired by {DNA}-sequence alignment, we devise a method to use multiple sequence alignment to automatically compare output from multiple third party{OMR}tools and perform automatic error-correction of pitch and duration of notes. We perform tests on a corpus of 49 one-page scores of varying quality. Our method on average reduces the amount of errors from an ensemble of 4 commercial {OMR} tools. The method achieves, on average, fewer errors than each recognizer by itself, but statistical tests show that it is sig- nificantly better than only 2 of the 4 commercial recogniz- ers. The results suggest that recognizers may be improved somewhat by sequence alignment and voting, but that more elaborate methods may be needed to obtain substantial im- provements. All software, scanned music data used for testing, and experiment protocols are open source and available at: http://code.google.com/p/omr-errorcorrection/},

file = {:pdfs/2011 - Using Sequence Alignment and Voting to Improve Optical Music Recognition from Multiple Recognizers.pdf:PDF},

isbn = {9780615548654},

url = {http://www.ismir2011.ismir.net/papers/PS3-9.pdf},

}

@InProceedings{Bui2014,

author = {Bui, Hoang-Nam and Na, Iin-Seop and Kim, Soo-Hyung},

booktitle = {22nd International Conference on Pattern Recognition},

title = {Staff Line Removal Using Line Adjacency Graph and Staff Line Skeleton for Camera-Based Printed Music Scores},

year = {2014},

pages = {2787--2789},

abstract = {On camera-based music scores, curved and uneven staff-lines tend to

incur more frequently, and with the loss in performance of binarization

methods, line thickness variation and space variation between lines

are inevitable. We propose a novel and effective staff-line removal

method based on following 3 main ideas. First, the state-of-the-art

staff-line detection method, Stable Path, is used to extract staff-line

skeletons of the music score. Second, a line adjacency graph (LAG)

model is exploited in a different manner of over segmentation to

cluster pixel runs generated from the run-length encoding (RLE) of

the image. Third, a two-pass staff-line removal pipeline called filament

filtering is applied to remove clusters lying on the staff-line.

Our method shows impressive results on music score images captured

from cameras, and gives high performance when applied to the ICDAR/GREC

2013 database.},

doi = {10.1109/ICPR.2014.480},

file = {:pdfs/2014 - Staff Line Removal Using Line Adjacency Graph and Staff Line Skeleton for Camera-Based Printed Music Scores.pdf:PDF},

issn = {1051-4651},

keywords = {filtering theory;graph theory;image coding;image denoising;image segmentation;music;runlength codes;visual databases;ICDAR-GREC 2013 database;LAG model;binarization methods;camera-based printed music scores;cluster pixel;filament filtering;image RLE;line adjacency graph;line thickness variation;music score images;over segmentation;run-length encoding;space variation;stable path;staff line skeleton;staff-line detection method;two-pass staff-line removal pipeline;Cameras;Databases;Educational institutions;Music;Skeleton;Text analysis;line adjacency graph;music score recognition;optical music recognition;staff-line},

}

@InProceedings{Bulis1992,

author = {Bulis, Alex and Almog, Roy and Gerner, Moti and Shimony, Uri},

booktitle = {International Computer Music Conference},

title = {Computerized recognition of hand-written musical notes},

year = {1992},

pages = {110--112},

file = {:pdfs/1992 - Computerized recognition of hand-written musical notes.pdf:PDF},

url = {http://hdl.handle.net/2027/spo.bbp2372.1992.029},

}

@Article{Bullen2008,

author = {Bullen, Andrew H.},

journal = {code4lib Journal},

title = {Bringing Sheet Music to Life: My Experiences with {OMR}},

year = {2008},

issn = {1940-5758},

number = {84},

volume = {3},

file = {:pdfs/2008 - Bringing Sheet Music to Life - My Experiences with OMR.pdf:PDF},

url = {http://journal.code4lib.org/articles/84},

}

@InProceedings{Burgoyne2007,

author = {Burgoyne, John Ashley and Pugin, Laurent and Eustace, Greg and Fujinaga, Ichiro},

booktitle = {8th International Conference on Music Information Retrieval},

title = {A Comparative Survey of Image Binarisation Algorithms for Optical Recognition on Degraded Musical Sources},

year = {2007},

file = {:pdfs/2007 - A Comparative Survey of Image Binarisation Algorithms for Optical Recognition on Degraded Musical Sources.pdf:PDF},

url = {http://ismir2007.ismir.net/proceedings/ISMIR2007_p509_burgoyne.pdf},

}

@InProceedings{Burgoyne2008,

author = {Burgoyne, John Ashley and Devaney, Johanna and Pugin, Laurent and Fujinaga, Ichiro},

booktitle = {9th International Conference on Music Information Retrieval},

title = {Enhanced Bleedthrough Correction for Early Music Documents with Recto-Verso Registration},

year = {2008},

address = {Philadelphia, PA},

pages = {407--412},

file = {:pdfs/2008 - Enhanced Bleedthrough Correction for Early Music Documents with Recto Verso Registration.pdf:PDF},

url = {http://www.ismir2008.ismir.net/papers/ISMIR2008_221.pdf},

}

@InProceedings{Burgoyne2009,

author = {Burgoyne, John Ashley and Ouyang, Yue and Himmelman, Tristan and Devaney, Johanna and Pugin, Laurent and Fujinaga, Ichiro},

booktitle = {10th International Society for Music Information Retrieval Conference},

title = {Lyric Extraction and Recognition on Digital Images of Early Music Sources},

year = {2009},

address = {Kobe, Japan},

pages = {723--727},

file = {:pdfs/2009 - Lyric Extraction and Recognition on Digital Images of Early Music Sources.pdf:PDF},

url = {http://ismir2009.ismir.net/proceedings/OS8-3.pdf},

}

@InCollection{Burgoyne2015,

author = {Burgoyne, John Ashley and Fujinaga, Ichiro and Downie, J. Stephen},

booktitle = {A New Companion to Digital Humanities},

publisher = {Wiley Blackwell},

title = {Music Information Retrieval},

year = {2015},

editor = {Schreibman, Susan and Siemens, Ray and Unsworth, John},

isbn = {9781118680605},

pages = {213--228},

abstract = {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." MIR was born from computational musicology in the 1960s and

has since grown to have links with music cognition and audio engineering,

a dedicated annual conference (ISMIR) and an annual evaluation campaign

(MIREX). MIR combines machine learning with expert human knowledge

to use digital music data - images of music scores, "symbolic" data

such as MIDI files, audio, and metadata about musical items - for

information retrieval, classification and estimation, or sequence

labeling. This chapter gives a brief history of MIR, introduces classical

MIR tasks from optical music recognition to music recommendation

systems, and outlines some of the key questions and directions for

future developments in MIR. © 2016 John Wiley & Sons, Ltd.},

affiliation = {Music Cognition Group, University of Amsterdam, Netherlands; Schulich School of Music, McGill University, Canada; Graduate School of Library and Information Science, University of Illinois, United States},

author_keywords = {Audio engineering; Classification; Computational musicology; Evaluation; ISMIR; Machine learning; MIREX; Music cognition; Music information retrieval (MIR); Sequence labeling},

correspondence_address1 = {Burgoyne, J.A.; Music Cognition Group, University of AmsterdamNetherlands},

doi = {10.1002/9781118680605.ch15},

file = {:pdfs/2015 - Music Information Retrieval.pdf:PDF},

journal = {A New Companion to Digital Humanities},

}

@InProceedings{Burlet2012,

author = {Burlet, Gregory and Porter, Alastair and Hankinson, Andrew and Fujinaga, Ichiro},

booktitle = {13th International Society for Music Information Retrieval Conference},

title = {Neon.js: Neume Editor Online},

year = {2012},

address = {Porto, Portugal},

pages = {121--126},

file = {:pdfs/2012 - Neon.js - Neume Editor Online.pdf:PDF},

url = {http://ismir2012.ismir.net/event/papers/121_ISMIR_2012.pdf},

}

@PhdThesis{Byrd1984,

author = {Byrd, Donald},

school = {Indiana University},

title = {Music Notation by Computer},

year = {1984},

file = {:pdfs/1984 - Music Notation by Computer.pdf:PDF},

keywords = {music notation},

url = {https://dl.acm.org/citation.cfm?id=911809},

}

@Article{Byrd2003,

author = {Byrd, Donald and Isaacson, Eric},

journal = {Computer Music Journal},

title = {A Music Representation Requirement Specification for Academia},

year = {2003},

issn = {01489267, 15315169},

number = {4},

pages = {43--57},

volume = {27},

file = {:pdfs/2003 - A Music Representation Requirement Specification for Academia.pdf:PDF},

publisher = {The MIT Press},

url = {http://www.jstor.org/stable/3681900},

}

@InProceedings{Byrd2006,

author = {Byrd, Donald and Schindele, Megan},

booktitle = {7th International Conference on Music Information Retrieval},

title = {Prospects for Improving {OMR} with Multiple Recognizers},

year = {2006},

pages = {41--46},

file = {:pdfs/2006 - Prospects for Improving OMR with Multiple Recognizers.pdf:PDF},

isbn = {1-55058-349-2},

keywords = {classifier, omr, optical music recognition, to classify},

url = {http://ismir2006.ismir.net/PAPERS/ISMIR06155_Paper.pdf},

}

@InProceedings{Byrd2009,

author = {Byrd, Donald},

booktitle = {Knowledge representation for intelligent music processing},

title = {Studying Music is Difficult and Important: Challenges of Music Knowledge Representation},

year = {2009},

address = {Wadern, Germany},

editor = {Eleanor Selfridge-Field and Frans Wiering and Geraint A. Wiggins},

number = {09051},

organization = {Leibniz-Center for Informatics},

publisher = {Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik, Germany},

series = {Dagstuhl Seminar Proceedings},

file = {:pdfs/2009 - Studying Music Is Difficult and Important - Challenges of Music Knowledge Representation.pdf:PDF},

issn = {1862-4405},

url = {http://drops.dagstuhl.de/opus/volltexte/2009/1987},

}

@TechReport{Byrd2010,

author = {Byrd, Donald and Guerin, William and Schindele, Megan and Knopke, Ian},

institution = {Indiana University},

title = {{OMR} Evaluation and Prospects for Improved {OMR} via Multiple Recognizers},

year = {2010},

address = {Bloomington, IN, USA},

file = {:pdfs/2010 - OMR evaluation and prospects for improved OMR via multiple recognizers.pdf:PDF},

publisher = {Indiana University},

url = {http://homes.soic.indiana.edu/donbyrd/MROMR2010Pap/OMREvaluation Prospects4MROMR.doc},

}

@Article{Byrd2015,

author = {Byrd, Donald and Simonsen, Jakob Grue},

journal = {Journal of New Music Research},

title = {Towards a Standard Testbed for Optical Music Recognition: Definitions, Metrics, and Page Images},

year = {2015},

issn = {0929-8215},

number = {3},

pages = {169--195},

volume = {44},

abstract = {We posit that progress in Optical Music Recognition (OMR) has been held up for years by the absence of anything resembling the standard testbeds in use in other fields that face difficult evaluation problems. One example of such a field is text information retrieval (IR), where the Text Retrieval Conference (TREC) has annually-renewed IR tasks with accompanying data sets. In music informatics, the Music Information Retrieval Exchange (MIREX), with its annual tests and meetings held during the ISMIR conference, is a close analog to TREC; but MIREX has never had an OMR track or a collection of music such a track could employ. We describe why the absence of an OMR testbed is a problem and how this problem may be mitigated. To aid in the establishment of a standard testbed, we provide (1) a set of definitions for the complexity of music notation; (2) a set of performance metrics for OMR tools that gauge score complexity and graphical quality; and (3) a small corpus of music for use as a baseline for a proper OMR testbed.},

affiliation = {Indiana University, United States; Department of Computer Science, University of Copenhagen (DIKU), Denmark},

author_keywords = {empirical evaluation; notation; notation complexity; optical music recognition},

doi = {10.1080/09298215.2015.1045424},

file = {:pdfs/2015 - Towards a Standard Testbed for Optical Music Recognition_ Definitions, Metrics, and Page Images.pdf:PDF},

publisher = {Taylor and Francis Ltd.},

}

@TechReport{Byrd2016,

author = {Byrd, Donald and Isaacson, Eric},

institution = {Indiana University, Bloomington},

title = {A Music Representation Requirement Specification for Academia},

year = {2016},

file = {:pdfs/2016 - A Music Representation Requirement Specification for Academia.pdf:PDF},

url = {http://homes.sice.indiana.edu/donbyrd/Papers/MusicRepReqForAcad.doc},

}

@InProceedings{Calvo-Zaragoza2014,

author = {Calvo-Zaragoza, Jorge and Oncina, Jose},

booktitle = {22nd International Conference on Pattern Recognition},

title = {Recognition of Pen-Based Music Notation: The {HOMUS} Dataset},

year = {2014},

pages = {3038--3043},

publisher = {Institute of Electrical \& Electronics Engineers (IEEE)},

abstract = {A profitable way of digitizing a new musical composition is by using a pen-based (online) system, in which the score is created with the sole effort of the composition itself. However, the development of such systems is still largely unexplored. Some studies have been carried out but the use of particular little datasets has led to avoid objective comparisons between different approaches. To solve this situation, this work presents the Handwritten Online Musical Symbols (HOMUS) dataset, which consists of 15200 samples of 32 types of musical symbols from 100 different musicians. Several alternatives of recognition for the two modalities -online, using the strokes drawn by the pen, and offline, using the image generated after drawing the symbol- are also presented. Some experiments are included aimed to draw main conclusions about the recognition of these data. It is expected that this work can establish a binding point in the field of recognition of online handwritten music notation and serve as a baseline for future developments.},

doi = {10.1109/ICPR.2014.524},

file = {:pdfs/2014 - Recognition of Pen-Based Music Notation - The HOMUS dataset.pdf:PDF},

groups = {datasets},

issn = {1051-4651},

keywords = {handwritten character recognition;image recognition;information retrieval;light pens;music;HOMUS dataset;data recognition;handwritten online musical symbols dataset;image generation;musical composition digitization;online handwritten music notation recognition;online modality recognition;pen-based music notation recognition;symbol drawing;Error analysis;FCC;Handwriting recognition;Hidden Markov models;Kernel;Music;Support vector machines},

}

@Article{Calvo-Zaragoza2015,

author = {Calvo-Zaragoza, Jorge and Barbancho, Isabel and Tard{\'o}n, Lorenzo J. and Barbancho, Ana M.},

journal = {Pattern Analysis and Applications},

title = {Avoiding staff removal stage in optical music recognition:{~}application to scores written in white mensural notation},

year = {2015},

issn = {1433-755X},

number = {4},

pages = {933--943},

volume = {18},

abstract = {Staff detection and removal is one of the most important issues in

optical music recognition (OMR) tasks since common approaches for

symbol detection and classification are based on this process. Due

to its complexity, staff detection and removal is often inaccurate,

leading to a great number of errors in posterior stages. For this

reason, a new approach that avoids this stage is proposed in this

paper, which is expected to overcome these drawbacks. Our approach

is put into practice in a case of study focused on scores written

in white mensural notation. Symbol detection is performed by using

the vertical projection of the staves. The cross-correlation operator

for template matching is used at the classification stage. The goodness

of our proposal is shown in an experiment in which our proposal attains

an extraction rate of 96 {\%} and a classification rate of 92 {\%},

on average. The results found have reinforced the idea of pursuing

a new research line in OMR systems without the need of the removal

of staff lines.},

doi = {10.1007/s10044-014-0415-5},

file = {:pdfs/2015 - Avoiding staff removal stage in optical music recognition - application to scores written in white mensural notation.pdf:PDF},

}

@Article{Calvo-Zaragoza2015a,

author = {Calvo-Zaragoza, Jorge and Oncina, Jose},

journal = {Lecture Notes in Computer Science},

title = {Clustering of strokes from pen-based music notation: An experimental study},

year = {2015},

issn = {0302-9743},