Explore the vast range of titles available.

Manual transcription of music is a tedious work, which can be greatly facilitated by optical music recognition (OMR) software. However, OMR software is error prone in particular for older handwritten documents. This paper introduces and evaluates a pipeline that automates the entire OMR workflow in the context of the Corpus Monodicum project, enabling the transcription of historical chants. In addition to typical OMR tasks such as staff line detection, layout detection, and symbol recognition, the rarely addressed tasks of text and syllable recognition and assignment of syllables to symbols are tackled. For quantitative and qualitative evaluation, we use documents written in square notation developed in the 11th–12th century, but the methods apply to many other notations as well. Quantitative evaluation measures the number of necessary interventions for correction, which are about 0.4% for layout recognition including the division of text in chants, 2.4% for symbol recognition including pitch and reading order and 2.3% for syllable alignment with correct text and symbols. Qualitative evaluation showed an efficiency gain compared to manual transcription with an elaborate tool by a factor of about 9. In a second use case with printed chants in similar notation from the “Graduale Synopticum”, the evaluation results for symbols are much better except for syllable alignment indicating the difficulty of this task.

This paper deals with the effect of exploiting background knowledge for improving an OMR (Optical Music Recognition) deep learning pipeline for transcribing medieval, monophonic, handwritten music from the 12th–14th century, whose usage has been neglected in the literature. Various types of background knowledge about overlapping notes and text, clefs, graphical connections (neumes) and their implications on the position in staff of the notes were used and evaluated. Moreover, the effect of different encoder/decoder architectures and of different datasets for training a mixed model and for document-specific fine-tuning based on an extended OMR pipeline with an additional post-processing step were evaluated. The use of background models improves all metrics and in particular the melody accuracy rate (mAR), which is based on the insert, delete and replace operations necessary to convert the generated melody into the correct melody. When using a mixed model and evaluating on a different dataset, our best model achieves without fine-tuning and without post-processing a mAR of 90.4%, which is raised by nearly 30% to 93.2% mAR using background knowledge. With additional fine-tuning, the contribution of post-processing is even greater: the basic mAR of 90.5% is raised by more than 50% to 95.8% mAR.

Even today, the automatic digitisation of scanned documents in general, but especially the automatic optical music recognition (OMR) of historical manuscripts, still remains an enormous challenge, since both handwritten musical symbols and text have to be identified. This paper focuses on the Medieval so-called square notation developed in the 11th–12th century, which is already composed of staff lines, staves, clefs, accidentals, and neumes that are roughly spoken connected single notes. The aim is to develop an algorithm that captures both the neumes, and in particular its melody, which can be used to reconstruct the original writing. Our pipeline is similar to the standard OMR approach and comprises a novel staff line and symbol detection algorithm based on deep Fully Convolutional Networks (FCN), which perform pixel-based predictions for either staff lines or symbols and their respective types. Then, the staff line detection combines the extracted lines to staves and yields an F 1 -score of over 99% for both detecting lines and complete staves. For the music symbol detection, we choose a novel approach that skips the step to identify neumes and instead directly predicts note components (NCs) and their respective affiliation to a neume. Furthermore, the algorithm detects clefs and accidentals. Our algorithm predicts the symbol sequence of a staff with a diplomatic symbol accuracy rate (dSAR) of about 87%, which includes symbol type and location. If only the NCs without their respective connection to a neume, all clefs and accidentals are of interest, the algorithm reaches an harmonic symbol accuracy rate (hSAR) of approximately 90%. In general, the algorithm recognises a symbol in the manuscript with an F 1 -score of over 96%.

After manhattan, wolff found Boston sleepy and sedate—a perfect place to study the canon of dead languages, but less apt for radical experiments in sound. Harvard itself was notoriously conservative, not only in its social habits and politics but in its cultural life. Music composition on campus was staid, though avid, its thriving academic program overseen by Walter Piston and Randall Thompson, both eminent composers with Old World regard for form, coherence, and balance. Although they guided their students (who included Leonard Bernstein and then neoclassicist Elliott Carter) into the modernism of Stravinsky, Bartok, Hindemith, and even Schoenberg, Piston

Signs and graphic characters are frozen acts that can be ascribed to hand and finger movements as well as arm and body gestures. The body’s ability to memorize movements, which are activated externally and informs actions like singing, is called cheironomy in music theory. This ensured an oral-gestic tradition before music was written down in mensural and neumatic notation, a process that was initially welcomed as a rationalizing advancement that fascilitated memory and made a more precise codification of musical meaning visable and readily accessible. The question remains, however, whether notation represents progress compared to a performance using hand gestures (whereby the oral-mimetic impulses of music are mostly lost), or whether present day conducting is able to surpass these original impulses.

Signs and graphic characters are frozen acts that can be ascribed to hand and finger movements as well as arm and body gestures. The body’s ability to memorize movements, which are activated externally and informs actions like singing, is called cheironomy in music theory. This ensured an oral-gestic tradition before music was written down in mensural and neumatic notation, a process that was initially welcomed as a rationalizing advancement that fascilitated memory and made a more precise codification of musical meaning visable and readily accessible. The question remains, however, whether notation represents progress compared to a performance using hand gestures (whereby the oral-mimetic impulses of music are mostly lost), or whether present day conducting is able to surpass these original impulses.

When a practical way of recording music in writing was invented in the early ninth century, it defined neither the pitches of specific notes in a melody, nor the intervallic relations between successive notes. Nineteenth-century views of such notations considered them primitive; more recent descriptions have recognised that precise pitch notation was not a basic aim. But how did ninth-century neumatic notations deal with pitch, and, if the role of memory was not usurped by written records, what role did notation fulfil? In this study, the interaction of memory and writing is explored. Notations written by a French and by a German scribe (F-La MS 239 and S-SG MS 359) are seen to follow different strategies for the arrangement of signs above the text, striking divergent visual balances between pitch information and the text–music link. In each notation the reader is led along a path of recall, with more or less emphatic written signals provided as required.

The increasing variety of digital tools available for medieval musicology research includes the new project Single Interface for Music Score Searching and Analysis (SIMSSA) at McGill University. Currently under development, SIMSSA has begun scanning medieval chant manuscripts and applying optical music recognition (OMR) software to search for musical content. Once thought to be nearly impossible owing to the complexity and stylistic variety of handwritten chant notation (neumes), SIMSSAs initial ventures have demonstrated that despite the hundreds of different types of medieval signs and the unique characteristics of scribes across medieval Europe, the musical, textual and liturgical content on manuscript pages can be isolated and identified. Manual entry of chant texts and melodies, which is routinely followed by a thorough review, will be supplanted by automated entry, ready for human proofreading. Hours of research time spent collecting data will be saved, and musicologists will be able to move towards analysis of the information much more quickly. With a potentially very large amount of digitized chant data extracted with reduced time and effort, the scope of computer applications for analysis and comparison is considerable. Thriving on the wealth of online digital image libraries, where high-quality photographs of thousands of pages of medieval books are freely available, SIMSSA will not only complement the digital tools currently available to medieval chant researchers, but will bring their varied interests together in a unified online research environment.

This article describes and analyzes two leaves from a mid-eleventh-century Gradual that survive today in the Franciscan Library repository in Dublin’s Trinity College Library and in the Archivo Histórico Nacional in Madrid. The fragments contain parts of the masses for St. Lawrence and for St. Martin, including introit tropes, a number of prosulas for the alleluia, and the beginnings of the prose for each mass, in Beneventan script. Despite the small amount of music and text that survives, a collation with manuscripts from Benevento and Montecassino allows us to posit that the Gradual was copied probably at but not for Montecassino, that the context of some of the pieces as cited in the extended tonary in MC 318 points to the cathedral of Capua as the place for which the Gradual was copied, and that these two leaves are virtually the only surviving monument of the Capua liturgy in the eleventh century. A number of the prosulas are apparently unica, which adds considerably to our knowledge of the repertory of prosulas south of Rome. Moreover, the notation of the proses was clearly modeled on an exemplar written in a manner used virtually nowhere else in Europe outside St. Gall and Reichenau, indicating that in some cases the Notkerian canon reached southern Italy in versions unmediated by north Italian transmission. The concordance pattern of one of the proses also indicates apparently unmediated transmission of parts of the Beneventan repertory to southern France, confirming direct contacts between Aquitaine and Benevento that have hitherto been observed only in the transmission of Aquitanian material to Italy.

In 1984, John Stinson and Brian Parish developed Scribe, a computer program to encode every meaningful mark on each page of a medieval music manuscript and produce an on-screen representation of these data in both medieval and modern notation. Scribe data have proved essential for creating statistical and comparative analyses, compositional analyses and producing online thematic indices for the Medieval Music Database over a large body of music. Even though the Scribe still functions in cross-platform DOS-emulated computer environments, the growth of Digital Humanities, linked open data and enormous potential for online research collaboration offers a series of opportunities for encoded medieval music notation data. This report details the authors' efforts since 2013 in converting Scribe's data into open access data based upon the standard being developed by the Music Encoding Initiative (MEI). When coupled with recent developments in the Standard Music Font Layout (SMuFL) project, our new Scnbe-based module, known as NeoScribe, offers significant enhancements to the MEI standard that stand to benefit current and future developments in digital musicology.