Peter Van Kranenburg

This paper takes as an example the envisioned portal of the newly started Polifonia project that interlinks resources from very rich, old, established archives while making optimal use of the latest semantic web technologies. In the project, ten research pilots, spanning from historical bells and organ heritage, classification of polyphonic notated music, to the historical role of music in children's lives, form the driving force behind the development of the dedicated interface. Based on a mixture of participation and participatory observation, we describe and reflect on the processes involved in making the portal. In other words - exemplified with the case of Polifonia - we reflect on the role of interfaces (of various types, shapes, manifestations and/or durations) to organise knowledge in an interdisciplinary project. In particular, we focus on the role of data management within the project as a key component of research methodology and cross-disciplinary collaboration, rath...

The task of melodic segmentation is a long-standing MIR task that has not yet been solved. In this paper, a rule mining algorithm is employed to find rule sets that classify notes within their local context as phrase boundaries. Both the discovered rule set and a Random Forest Classifier trained on the same data set outperform previous methods on the task of melodic segmentation of melodies from the Essen Folk Song Collection, the Meertens Tune Collections, and the set of Bach Chorales. By inspecting the rules, some important clues are revealed about what constitutes a melodic phrase boundary, notably a prevalence of rhythm features over pitch features.

The Meertens Tune Collections (MTC) and the Essen Folk Song Collections include various data sets with melodic data. The melodies are provided in Humdrum **kern encoding and as MIDI sequences. In many cases, a representation of the melodies as sequences of feature values is needed rather than encoded scores. The present dataset provides such feature sequences. It is accompanied by a Python module that offers functionality to load and filter the sequences: MTCFeatures. The documentation of MTCFeatures contains a detailed description of the features. The following melody collections are included: MTC-ANN-2.0.1 - A small set of 360 richly annotated melodies from Dutch sources. MTC-FS-INST-2.0 - A large set of c. 18 thousand melodies from Dutch sources. ESSEN Folksong Collection - A set of more than 8 thousand folk song melodies mainly from Germany. For more information on the contents of the Meertens Tune Collections, please visit http://www.liederenbank.nl/mtc/. For the Essen Folk Son...

The Mozarabic rite provided the dominant context for Christian worship on the Iberian Peninsula and Southern France from the sixth till eleventh centuries. Over 5,000 chants of the Mozarabic rite are preserved in neumatic contour notation. Since pitch-readable notation only became in use in the eleventh century and hardly any Mozarabic chant was found in such notation, scholars believe that most Mozarabic melodies are irretrievably lost. Based on similarities between the chant of Mozarabic and other rites, this paper presents a method for the computational composition of melodies agreeing in all detail with our knowledge of the early Mozarabic neumatic notation. We first describe how we came to look for such a method. Then we give a detailed description of the eight steps of the method. Finally, we propose objective criteria that supposedly are indicative for the authenticity of our compositions, we restate our goals, and refer to several sound examples on the internet.

During the last decade, a rapidly increasing amount of work has been done in the area of Digital Humanities. Conferences were established. Research programs were launched. Departments and institutes were founded. Although there is still much confusion and debate about the essence of the field, some recurring themes can be observed. It seems that much of the current effort goes into creating research environments and infrastructures combining large interoperable, harmonized data sets and user friendly search and visualization tools that enable humanities researchers to search and explore the data and make new, previously unimaginable, discoveries. Among these humanities data sets, there are musical data as well. Ethnomusicological archives have been digitized. Many scores of important composers are currently available in various digital formats. Massive amounts of user tags from services such as Last.fm are available. This enables data-rich research on music on a large scale. The que...

ion level of the viewpoints should be high enough to capture variability in the melodies as caused both by the process of oral transmission and by variations in choices that were made in the process of transcription into music notation. To achieve a suitable level of abstraction, we measure relative values for all viewpoints derived from pitch or duration. For the current study we define the following viewpoints: phrpos, which records whether the note is the first in a phrase, the last in a phrase, or inside a phrase; intref, which represents the scale degree of the note given the key of the song; c3i(level), which records whether the metric level of a note is higher, lower or equal with respect to the previous note; c3(dur), which records whether the note is shorter, equal, or longer in duration than the previous note; c3(pitch), which records whether the note is higher, equal, or lower in pitch than the previous note; c5(pitch, 3), which records whether the note was approached by ...

The historically developed practice of learning to play a music instrument from notes instead of by imitation or improvisation makes it possible to contrast two types of skilled musicians characterized not only by dissimilar performance practices, but also disparate methods of audiomotor learning. In a recent fMRI study comparing these two groups of musicians while they either imagined playing along with a recording or covertly assessed the quality of the performance, we observed activation of a right-hemisphere network of posterior superior parietal and dorsal premotor cortices in improvising musicians, indicating more efficient audiomotor transformation. In the present study, we investigated the detailed performance characteristics underlying the ability of both groups of musicians to replicate music on the basis of aural perception alone. Twenty-two classically-trained improvising and score-dependent musicians listened to short, unfamiliar two-part excerpts presented with headpho...

We present a system to extract ranked lists of actors from fairytales ordered by importance. This task requires more than a straightforward application of generic methods such as Named Entity Recognition. We show that by focusing on two specific linguistic constructions that reflect the intentionality of a subject, direct and indirect speech, we obtain a high-precision method to extract the cast of a story. The system we propose contains a new method based on the dispersion of terms to rank the different cast members on a ...

This contribution aims to suggest some items for the research agenda of Computational Folk Song Research, based on a selective historic overview of the research tradition of Western Folk Song Research and on the current methods and foci of Computational Musicology and Music Information Retrieval. We specifically focus on folk songs from Western Europe, such as the Dutch or German. For example, the Meertens Tune Collections, consisting of thousands of digitized recordings, symbolic representations and metadata of folk songs from Dutch oral tradition, 1 or the EsAC Folksong Databases, which currently includes over 20,000 digitized song melodies from various countries in Europe and beyond (Schaffrath, 1995).

Many Western songs are hierarchically structured in stanzas and phrases. The melody of the song is repeated for each stanza, while the lyrics vary. Each stanza is subdi- vided into phrases. It is to be expected that melodic and textual formulas at the end of the phrases offer intrinsic clues of closure to a listener or singer. In the current paper we aim at a method to detect such cadences in symbolically encoded folk songs. We take a trigram approach in which we classify trigrams of notes and pitches as cadential or as non-cadential. We use pitch, contour, rhythmic, textual, and contextual features, and a group of features based on the conditions of closure as stated by Narmour [11]. We employ a random forest classification algorithm. The pre- cision of the classifier is considerably improved by taking the class labels of adjacent trigrams into account. An ablation study shows that none of the kinds of features is suffi- cient to account for good classification, while some of the g...

ABSTRACT In this article we determine the role of different musical features for the human categorization of folk songs into tune families in a large collection of Dutch folk songs. Through an annotation study we investigate the relation between musical features, perceived similarity and human categorization in music. We introduce a newly developed annotation method which is used to create an annotation data set for 360 folk song melodies in 26 tune families. This dataset delivers valuable information on the contribution of musical features to the process of categorization which is based on assessing the similarity between melodies. The analysis of the annotation data set reveals that the importance of single musical features for assessing similarity varies both between and within tune families. In general, the recurrence of short characteristic motifs is most relevant for the perception of similarity between songs belonging to the same tune family. Global melodic features often used for the description of melodies (such as melodic contour) play a less important role. The annotation data set is a valuable resource for further research on melodic similarity and can be used as enriched “ground truth” to test various kinds of retrieval algorithms in Music Information Retrieval. Our annotation study exemplifies that assessing similarity is crucial for human categorization processes, which has been questioned within Cognitive Science in the context of rule-based approaches to categorization.

We present a method to classify audio recordings of folk songs into tune families. For this, we segment both the query recording and the recordings in the collection. The segments can be used to relate recordings to each other by evaluating the recurrence of similar melodic patterns. We compare a segmentation that results in what can be considered cognitive units to a segmentation into segments of fixed length. It appears that the use of 'cognitive'segments results in higher classification accuracy.

The cantillation signs of the Jewish Torah trope are of particular interest to chant scholars interested in the gradual transformation of oral music performance into notation. Each sign, placed above or below the text, acts as a “melodic idea” which either connects or divides words in order to clarify the syntax, punctuation and, in some cases, meaning of the text. Unlike standard music notation, the interpretations of each sign are flexible and influenced by regional traditions, practices of given Jewish communities, larger musical ...