Exploring the Classification of Pipe Organ Sounds: Recognizing Instruments, Organ Types, and Registrations

Vince During; Pablo Dumenil; Peter van Kranenburg

doi:10.5281/zenodo.17498162

Exploring the Classification of Pipe Organ Sounds: Recognizing Instruments, Organ Types, and Registrations

Vince During
, Pablo Dumenil
, Peter van Kranenburg

Sub Music Information Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

Classification of pipe organ sounds is challenging as the pipe organ has a huge variety of timbres depending on the selection of stops and the type of the instrument. Recent advances in foundational models for audio enable the exploration of classification tasks for pipe organ audio recordings. We focus on Organ Type Recognition, Organ Identification, and Registration Recognition (both intra-track and for full tracks). Employing BYOL-A embeddings and the multi-layer perceptron, we achieve impressive classification results.

Original language	English
Title of host publication	Proceedings of the 17th International Symposium on Computer Music Multidisciplinary Research
Place of Publication	London
Pages	298-306
DOIs	https://doi.org/10.5281/zenodo.17498162
Publication status	Published - 3 Nov 2025
Event	17th International Symposium on Computer Music Multidisciplinary Research - University College London, London, United Kingdom Duration: 3 Nov 2025 → 7 Nov 2025 https://cmmr2025.prism.cnrs.fr

Conference

Conference	17th International Symposium on Computer Music Multidisciplinary Research
Abbreviated title	CMMR 2025
Country/Territory	United Kingdom
City	London
Period	3/11/25 → 7/11/25
Internet address	https://cmmr2025.prism.cnrs.fr

Access to Document

10.5281/zenodo.17498162Licence: CC BY

CMMR2025_O7_3Final published version, 1.6 MBLicence: CC BY

https://zenodo.org/records/17498163Licence: CC BY

Cite this

@inproceedings{b74fae43279944f6b4b5ecf094a14d03,

title = "Exploring the Classification of Pipe Organ Sounds: Recognizing Instruments, Organ Types, and Registrations",

abstract = "Classification of pipe organ sounds is challenging as the pipe organ has a huge variety of timbres depending on the selection of stops and the type of the instrument. Recent advances in foundational models for audio enable the exploration of classification tasks for pipe organ audio recordings. We focus on Organ Type Recognition, Organ Identification, and Registration Recognition (both intra-track and for full tracks). Employing BYOL-A embeddings and the multi-layer perceptron, we achieve impressive classification results.",

author = "Vince During and Pablo Dumenil and \{van Kranenburg\}, Peter",

year = "2025",

month = nov,

day = "3",

doi = "10.5281/zenodo.17498162",

language = "English",

pages = "298--306",

booktitle = "Proceedings of the 17th International Symposium on Computer Music Multidisciplinary Research",

note = "17th International Symposium on Computer Music Multidisciplinary Research, CMMR 2025 ; Conference date: 03-11-2025 Through 07-11-2025",

url = "https://cmmr2025.prism.cnrs.fr",

}

During, V, Dumenil, P & van Kranenburg, P 2025, Exploring the Classification of Pipe Organ Sounds: Recognizing Instruments, Organ Types, and Registrations. in Proceedings of the 17th International Symposium on Computer Music Multidisciplinary Research. London, pp. 298-306, 17th International Symposium on Computer Music Multidisciplinary Research, London, United Kingdom, 3/11/25. https://doi.org/10.5281/zenodo.17498162

Exploring the Classification of Pipe Organ Sounds: Recognizing Instruments, Organ Types, and Registrations. / During, Vince; Dumenil, Pablo; van Kranenburg, Peter.
Proceedings of the 17th International Symposium on Computer Music Multidisciplinary Research. London, 2025. p. 298-306.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Exploring the Classification of Pipe Organ Sounds: Recognizing Instruments, Organ Types, and Registrations

AU - During, Vince

AU - Dumenil, Pablo

AU - van Kranenburg, Peter

PY - 2025/11/3

Y1 - 2025/11/3

N2 - Classification of pipe organ sounds is challenging as the pipe organ has a huge variety of timbres depending on the selection of stops and the type of the instrument. Recent advances in foundational models for audio enable the exploration of classification tasks for pipe organ audio recordings. We focus on Organ Type Recognition, Organ Identification, and Registration Recognition (both intra-track and for full tracks). Employing BYOL-A embeddings and the multi-layer perceptron, we achieve impressive classification results.

AB - Classification of pipe organ sounds is challenging as the pipe organ has a huge variety of timbres depending on the selection of stops and the type of the instrument. Recent advances in foundational models for audio enable the exploration of classification tasks for pipe organ audio recordings. We focus on Organ Type Recognition, Organ Identification, and Registration Recognition (both intra-track and for full tracks). Employing BYOL-A embeddings and the multi-layer perceptron, we achieve impressive classification results.

U2 - 10.5281/zenodo.17498162

DO - 10.5281/zenodo.17498162

M3 - Conference contribution

SP - 298

EP - 306

BT - Proceedings of the 17th International Symposium on Computer Music Multidisciplinary Research

CY - London

T2 - 17th International Symposium on Computer Music Multidisciplinary Research

Y2 - 3 November 2025 through 7 November 2025

ER -

Exploring the Classification of Pipe Organ Sounds: Recognizing Instruments, Organ Types, and Registrations

Abstract

Conference

Access to Document

Fingerprint

Cite this