Melodic Similarity through Shape Similarity

Urbano, Julián; Lloréns, Juan; Morato, Jorge; Sánchez-Cuadrado, Sonia

doi:10.1007/978-3-642-23126-1_21

Cited by 19 publications

(14 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we address diculties at generating missing links from a large linked dataset representing symbolic music notation, 26 The scores, all for voice, guitar, and piano (and with Musicnotes.com IDs MN0104281, MN0053744, MN0053244, MN0053764, and MN0053784) were retrieved from https: //www.musicnotes.com/sheetmusic/index/artists/Beatles-The/default.asp. the MIDI Linked Data Cloud, to related entities in other linked music metadata datasets.…”

Section: Discussionmentioning

confidence: 99%

“…With respect to such models, three approaches have been proposed [19]: those based on the computation of index terms, those based on sequence matching techniques, and those based on geometric methods, which can cope with polyphonic scores. Examples of the latter are the algorithms that are part of MelodyShape, 6 a Java library and tool for modelling melodic similarity [24,26]. One of these algorithms, ShapeH, has consistently obtained the best results [25] In what follows, we provide a summary of the dataset, 8 and we describe two important additions to it.…”

Section: Midi Similarity Measuresmentioning

confidence: 99%

“…Using transcriptions of ve randomly selected Beatles songs, all of which we know to be contained in the test set, we then created ve query les, each consisting of the rst four bars of the vocal melody of a song (note that the query can be any melodic line in a piece; from a user's perspective, however, the vocal melody seems a logical choice). 26 To account for tonal variability during data entry, each query le was transposed two, four and six semitones up as well as down-resulting in a total of 35 query les. Table 3 shows, for each query, the three les found to be most similar by the algorithm, as well as the similarity score per retrieved le.…”

mentioning

confidence: 99%

See 2 more Smart Citations

The Semantic Web MIDI Tape

Meroño‐Peñuela

Valk²,

Daga

et al. 2018

Proceedings of the 1st International Workshop on Semantic Applications for Audio and Music

View full text Add to dashboard Cite

The Linked Data paradigm has been used to publish a large number of musical datasets and ontologies on the Semantic Web, such as MusicBrainz, AcousticBrainz, and the Music Ontology. Recently, the MIDI Linked Data Cloud has been added to these datasets, representing more than 300,000 pieces in MIDI format as Linked Data, opening up the possibility for linking ne-grained symbolic music representations to existing music metadata databases. Despite the dataset making MIDI resources available in Web data standard formats such as RDF and SPARQL, the important issue of nding meaningful links between these MIDI resources and relevant contextual metadata in other datasets remains. A fundamental barrier for the provision and generation of such links is the diculty that users have at adding new MIDI performance data and metadata to the platform. In this paper, we propose the Semantic Web MIDI Tape, a set of tools and associated interface for interacting with the MIDI Linked Data Cloud by enabling users to record, enrich, and retrieve MIDI performance data and related metadata in native Web data standards. The goal of such interactions is to nd meaningful links between published MIDI resources and their relevant contextual metadata. We evaluate the Semantic Web MIDI Tape in various use cases involving user-contributed content, MIDI similarity querying, and entity recognition methods, and discuss their potential for nding links between MIDI resources and metadata.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Midi Similarity Measuresmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

The Semantic Web MIDI Tape

Meroño‐Peñuela

Valk²,

Daga

et al. 2018

Proceedings of the 1st International Workshop on Semantic Applications for Audio and Music

View full text Add to dashboard Cite

show abstract

“…Many models of musical similarity start from the assumption that a melody is a sequence of pitches, and so similarity relationships between melodies can be expressed in terms of relations in pitch and time. Some are thoroughly geometrical, representing a melody as a set of points in a pitch-time space and then measuring the distance between points (see, for example, Hofmann-Engl, 2003), or some other mechanism for measuring difference (e.g., difference between curves fitted to the notes, Urbano et al, 2011). Sometimes these measures of difference are mediated also by an alignment of the notes of one melody with another through a mechanism such as Dynamic Time Warping.…”

Section: Models Of Similaritymentioning

confidence: 99%

Interrogating Melodic Similarity: A Definitive Phenomenon or the Product of Interpretation?

Marsden

2012

Journal of New Music Research

View full text Add to dashboard Cite

The nature of melodic similarity is interrogated through a survey of the different means by which the phenomenon has been studied, examination of methods for measuring melodic similarity, a Monte Carlo analysis of data from the experiment which formed the basis for the 'ground truth' used in the MIREX 2005 contest on melodic similarity, and examples of interest in the music of Mozart. Melodic similarity has been studied by a number of means, sometimes quite contrasting, which lead to important differences in the light of the finding that similarity is dependent on context. Models of melodic similarity based on reduction show that the existence of multiple possible reductions forms a natural basis for similarity to depend on interpretation. Examination of the MIREX 2005 data shows wide variations in subjects' judgements of melodic similarity and some evidence that the perceived similarity between two melodies can be influenced by the presence of a third melody. Examples from Mozart suggest that he deliberately exploited the possibilities inherent in recognising similarity through different interpretations. It is therefore proposed that similarity be thought of not as a distinct and definite function of two melodies but as something created in the minds of those who hear the melodies.

show abstract

“…Two measures compared in our previous study-B-spline alignment (Urbano, Lloréns, Morato, & Sánchez-Cuadrado, 2011) and Implication-Realization structure alignment (Grachten, Arcos, & López de Mántaras, 2005)-were not evaluated in this study as in their current implementation, they do not allow determining the positions of occurrences in a melody.…”

Section: Introductionmentioning

confidence: 99%

Finding Occurrences of Melodic Segments in Folk Songs Employing Symbolic Similarity Measures

Janssen

Kranenburg

Volk

2017

Journal of New Music Research

View full text Add to dashboard Cite

Much research has been devoted to the classification of folk songs, revealing that variants are recognised based on salient melodic segments, such as phrases and motifs, while other musical material in a melody might vary considerably. In order to judge similarity of melodies on the level of melodic segments, a successful similarity measure is needed which will allow finding occurrences of melodic segments in folk songs reliably. The present study compares several such similarity measures from different music research domains: correlation distance, city block distance, Euclidean distance, local alignment, wavelet transform and structure induction. We evaluate the measures against annotations of phrase occurrences in a corpus of Dutch folk songs, observing whether the measures detect annotated occurrences at the correct positions. Moreover, we investigate the influence of music representation on the success of the various measures, and analyse the robustness of the most successful measures over subsets of the data. Our results reveal that structure induction is a promising approach, but that local alignment and city block distance perform even better when applied to adjusted music representations. These three methods can be combined to find occurrences with increased precision.

show abstract

Melodic Similarity through Shape Similarity

Cited by 19 publications

References 13 publications

The Semantic Web MIDI Tape

The Semantic Web MIDI Tape

Interrogating Melodic Similarity: A Definitive Phenomenon or the Product of Interpretation?

Finding Occurrences of Melodic Segments in Folk Songs Employing Symbolic Similarity Measures

Contact Info

Product

Resources

About