https://www.mdu.se/

mdu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
TOWARDS AN OBJECTIVE COMPARISON OF PANNING FEATURE ALGORITHMS FOR UNSUPERVISED LEARNING
Mälardalen University, Faculty of Engineering and Health Sciences, Department of Computer Science & Engineering.ORCID iD: 0000-0003-3232-191X
Spotify, Sweden.
2025 (English)In: Proceedings of the 28th International Conference on Digital Audio Effects (DAFx25), DAFx , 2025, p. 403-410Conference paper, Published paper (Refereed)
Abstract [en]

Estimations of panning attributes are an important feature to extract from a piece of recorded music, with downstream uses suchas classification, quality assessment, and listening enhancement.While several algorithms exist in the literature, there is currently no comparison between them and no studies to suggest which one is most suitable for any particular task. This paper compares four algorithms for extracting amplitude panning features with respect to their suitability for unsupervised learning. It finds synchronicities between them and analyses their results on a small set of commercial music excerpts chosen for their distinct panning features. The ability of each algorithm to differentiate between the tracks is analysed. The results can be used in future work to either select the most appropriate panning feature algorithm or create aversion customized for a particular task.

Place, publisher, year, edition, pages
DAFx , 2025. p. 403-410
Series
Proceedings of the International Conference on Digital Audio Effects, ISSN 2413-6700
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:mdh:diva-75358Scopus ID: 2-s2.0-105028974722OAI: oai:DiVA.org:mdh-75358DiVA, id: diva2:2025841
Conference
28th International Conference on Digital Audio Effects (DAFx25), Ancona, Italy, 2 - 5 September 2025 
Funder
Knowledge FoundationAvailable from: 2026-01-08 Created: 2026-01-08 Last updated: 2026-09-09Bibliographically approved
In thesis
1. Analysis of stereo image in vast repositories of recorded music
Open this publication in new window or tab >>Analysis of stereo image in vast repositories of recorded music
2026 (English)Licentiate thesis, comprehensive summary (Other academic)
Abstract [en]

Spatial information is crucial to the listener’s experience of music, and stereophonic recordings have long been the standard for capturing this spaciousness. Recent advancements in computing, coupled with the availability of new, very large musical corpora, have created opportunities for large-scale quantitative analysis of the stereo image of recorded music. In this licentiate thesis I address a key gap in current research: direct analysis of raw music recordings to describ ethe stereo image. The work comprises practice-led research, objective experiments, perceptual listening tests, and an extensive literature review. A combination of immersion in the creative aspects of stereo field and thorough mathematical evaluation of the recorded signals created a strong foundation for future research. The studies together revealed that while there are many existing stereo descriptors, the musical features visible to each one vary considerably and therefore have differing use cases. Moreover, they don’t always align with human perception.The combination of research methods was hence a highly effective way to critique the strengths and weakness of objective measurements. Future work should focus on applying and adapting the discovered methods to modern music datasets

Place, publisher, year, edition, pages
Västerås: Mälardalens universitet, 2026. p. 73
Series
Mälardalen University Press Licentiate Theses, ISSN 1651-9256 ; 388
National Category
Computer and Information Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:mdh:diva-78973 (URN)978-91-7485-770-2 (ISBN)
Presentation
2026-10-30, room Kappa, Mälardalens universitet, Västerås, 13:15 (English)
Opponent
Supervisors
Available from: 2026-09-10 Created: 2026-09-09 Last updated: 2026-10-09Bibliographically approved

Open Access in DiVA

fulltext(1070 kB)235 downloads
File information
File name FULLTEXT01.pdfFile size 1070 kBChecksum SHA-512
d8994aa082ab2e85e343fa9481c56d27f1917277e7bb6ddc8288b8394a83cc8eb9071cb8e8353ce4179a6c5f7841e141d0d2a89ea44a55d768f96709f10e5dbe
Type fulltextMimetype application/pdf

Other links

Scopushttps://dafx.de/paper-archive/2025/DAFx25_paper_26.pdf

Authority records

Mitic, Richard

Search in DiVA

By author/editor
Mitic, Richard
By organisation
Department of Computer Science & Engineering
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 239 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 1422 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf