Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › Towards Interpreting and Improving the Latent Space for Musical Chord Recognition

Publication

Towards Interpreting and Improving the Latent Space for Musical Chord Recognition

Nadar, Christon R.; Taenzer, Michael; Abeßer, Jakob (2022): Towards Interpreting and Improving the Latent Space for Musical Chord Recognition, in: Giuseppe Torre und Giuseppe Torre (Hrsg.), Standing wave : ICMC 2022 : International Computer Music Conference, University of Limerick, Ireland, 2022, San Francisco, California, USA: International Computer Music Association, Inc., S. 74–79.

Details

Faculty/Chair
Author
Nadar, Christon R.
Taenzer, Michael
Title of the compilation
Standing wave : ICMC 2022 : International Computer Music Conference, University of Limerick, Ireland, 2022
Editors
Torre, Giuseppe
Conference
ICMC 2022 : International Computer Music Conference, Limerick
Publisher Information
International Computer Music Association, Inc. : San Francisco, California, USA
Year of publication
2022
ISBN
978-0-9713192-6-4
Language
English
URL
Abstract

Automatic chord recognition (ACR) naturally faces musical ambiguities between chord classes. These can be responsible for many misclassifications, especially in large chord vocabularies. In this paper, we propose a metric learning approach utilizing a triplet loss for the task of ACR in order to reduce chord ambiguities. In particular, we investigate how metric learning with different triplet sampling strategies re-aligns the distances between different chord classes in the latent space. Our main finding is that metric learning significantly improves the ACR performance for two taxonomies with five and nine chord classes.

Keywords
Musical Chord Recognition
Peer Reviewed
yes
International Distribution
yes
Type
Conferenceobject
URI
Activation date
2025-11-26

Permalink: https://fis.uni-bamberg.de/handle/uniba/111765 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-16

Restricted read-only access: login, editing and submission are temporarily disabled.