On large-scale genre classification in symbolically encoded music by automatic identification of repeating patterns

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

The importance of repetitions in music is well-known. In this paper, we study music repetitions in the context of effective and efficient automatic genre classification in large-scale music-databases. We aim at enhancing the access and organization of pieces of music in Digital Libraries by allowing automatic categorization of entire collections by considering only their musical content. We handover to the public a set of genre-specific patterns to support research in musicology. The patterns can be used, for instance, to explore and analyze the relations between musical genres.

There are many existing algorithms that could be used to identify and extract repeating patterns in symbolically encoded music. In our case, the extracted patterns are used as representations of the pieces of music on the underlying corpus and, consecutively, to train and evaluate a classifier to automatically identify genres. In this paper, we apply two very fast algorithms enabling us to experiment on large and diverse corpora. Thus, we are able to find patterns with strong discrimination power that can be used in various applications. We carried out experiments on a corpus containing over 40,000 MIDI files annotated with at least one genre. The experiments suggest that our approach is scalable and capable of dealing with real-world-size music collections.
Original languageEnglish
Title of host publicationDLfM '18 Proceedings of the 5th International Conference on Digital Libraries for Musicology
Number of pages4
Place of PublicationNew York, NY
PublisherACM
Publication date28 Sep 2018
Pages34-37
ISBN (Electronic)978-1-4503-6522-2
DOIs
Publication statusPublished - 28 Sep 2018
MoE publication typeA4 Article in conference proceedings
EventDigital Libraries for Musicology 2018 - IRCAM, Paris, France
Duration: 28 Sep 201828 Sep 2018
https://dlfm.web.ox.ac.uk/workshops/dlfm-2018/programme

Fields of Science

  • 113 Computer and information sciences
  • 6131 Theatre, dance, music, other performing arts

Cite this

Ferraro, A., & Lemström, K. M. B. (2018). On large-scale genre classification in symbolically encoded music by automatic identification of repeating patterns. In DLfM '18 Proceedings of the 5th International Conference on Digital Libraries for Musicology (pp. 34-37). New York, NY: ACM. https://doi.org/10.1145/3273024.3273035
Ferraro, Andres ; Lemström, Kjell Michael Bernhard. / On large-scale genre classification in symbolically encoded music by automatic identification of repeating patterns. DLfM '18 Proceedings of the 5th International Conference on Digital Libraries for Musicology. New York, NY : ACM, 2018. pp. 34-37
@inproceedings{c669e0df5ebe438db6e8b0ee744132ce,
title = "On large-scale genre classification in symbolically encoded music by automatic identification of repeating patterns",
abstract = "The importance of repetitions in music is well-known. In this paper, we study music repetitions in the context of effective and efficient automatic genre classification in large-scale music-databases. We aim at enhancing the access and organization of pieces of music in Digital Libraries by allowing automatic categorization of entire collections by considering only their musical content. We handover to the public a set of genre-specific patterns to support research in musicology. The patterns can be used, for instance, to explore and analyze the relations between musical genres.There are many existing algorithms that could be used to identify and extract repeating patterns in symbolically encoded music. In our case, the extracted patterns are used as representations of the pieces of music on the underlying corpus and, consecutively, to train and evaluate a classifier to automatically identify genres. In this paper, we apply two very fast algorithms enabling us to experiment on large and diverse corpora. Thus, we are able to find patterns with strong discrimination power that can be used in various applications. We carried out experiments on a corpus containing over 40,000 MIDI files annotated with at least one genre. The experiments suggest that our approach is scalable and capable of dealing with real-world-size music collections.",
keywords = "113 Computer and information sciences, 6131 Theatre, dance, music, other performing arts",
author = "Andres Ferraro and Lemstr{\"o}m, {Kjell Michael Bernhard}",
year = "2018",
month = "9",
day = "28",
doi = "10.1145/3273024.3273035",
language = "English",
publisher = "ACM",
pages = "34--37",
booktitle = "DLfM '18 Proceedings of the 5th International Conference on Digital Libraries for Musicology",
address = "United States",

}

Ferraro, A & Lemström, KMB 2018, On large-scale genre classification in symbolically encoded music by automatic identification of repeating patterns. in DLfM '18 Proceedings of the 5th International Conference on Digital Libraries for Musicology. ACM, New York, NY, pp. 34-37, Digital Libraries for Musicology 2018, Paris, France, 28/09/2018. https://doi.org/10.1145/3273024.3273035

On large-scale genre classification in symbolically encoded music by automatic identification of repeating patterns. / Ferraro, Andres; Lemström, Kjell Michael Bernhard.

DLfM '18 Proceedings of the 5th International Conference on Digital Libraries for Musicology. New York, NY : ACM, 2018. p. 34-37.

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

TY - GEN

T1 - On large-scale genre classification in symbolically encoded music by automatic identification of repeating patterns

AU - Ferraro, Andres

AU - Lemström, Kjell Michael Bernhard

PY - 2018/9/28

Y1 - 2018/9/28

N2 - The importance of repetitions in music is well-known. In this paper, we study music repetitions in the context of effective and efficient automatic genre classification in large-scale music-databases. We aim at enhancing the access and organization of pieces of music in Digital Libraries by allowing automatic categorization of entire collections by considering only their musical content. We handover to the public a set of genre-specific patterns to support research in musicology. The patterns can be used, for instance, to explore and analyze the relations between musical genres.There are many existing algorithms that could be used to identify and extract repeating patterns in symbolically encoded music. In our case, the extracted patterns are used as representations of the pieces of music on the underlying corpus and, consecutively, to train and evaluate a classifier to automatically identify genres. In this paper, we apply two very fast algorithms enabling us to experiment on large and diverse corpora. Thus, we are able to find patterns with strong discrimination power that can be used in various applications. We carried out experiments on a corpus containing over 40,000 MIDI files annotated with at least one genre. The experiments suggest that our approach is scalable and capable of dealing with real-world-size music collections.

AB - The importance of repetitions in music is well-known. In this paper, we study music repetitions in the context of effective and efficient automatic genre classification in large-scale music-databases. We aim at enhancing the access and organization of pieces of music in Digital Libraries by allowing automatic categorization of entire collections by considering only their musical content. We handover to the public a set of genre-specific patterns to support research in musicology. The patterns can be used, for instance, to explore and analyze the relations between musical genres.There are many existing algorithms that could be used to identify and extract repeating patterns in symbolically encoded music. In our case, the extracted patterns are used as representations of the pieces of music on the underlying corpus and, consecutively, to train and evaluate a classifier to automatically identify genres. In this paper, we apply two very fast algorithms enabling us to experiment on large and diverse corpora. Thus, we are able to find patterns with strong discrimination power that can be used in various applications. We carried out experiments on a corpus containing over 40,000 MIDI files annotated with at least one genre. The experiments suggest that our approach is scalable and capable of dealing with real-world-size music collections.

KW - 113 Computer and information sciences

KW - 6131 Theatre, dance, music, other performing arts

U2 - 10.1145/3273024.3273035

DO - 10.1145/3273024.3273035

M3 - Conference contribution

SP - 34

EP - 37

BT - DLfM '18 Proceedings of the 5th International Conference on Digital Libraries for Musicology

PB - ACM

CY - New York, NY

ER -

Ferraro A, Lemström KMB. On large-scale genre classification in symbolically encoded music by automatic identification of repeating patterns. In DLfM '18 Proceedings of the 5th International Conference on Digital Libraries for Musicology. New York, NY: ACM. 2018. p. 34-37 https://doi.org/10.1145/3273024.3273035