Please use this identifier to cite or link to this item: doi:10.22028/D291-35132
Volltext verfügbar? / Dokumentlieferung
Title: What if the 'When' Implies the 'What'?: Human harmonic analysis datasets clarify the relative role of the separate steps in automatic tonal analysis
Author(s): Gotham, Mark
Kleinertz, Rainer
Weiß, Christof
Müller, Meinard
Klauk, Stephanie
Editor(s): Lee, Jin Ha
Lerch, Alexander
Duan, Zhiyao
Nam, Juhan
Rao, Preeti
Kranenburg, Peter van
Srinivasamurthy, Ajay
Language: English
Title: Proceedings of the 22nd International Society for Music Information Retrieval Conference
Startpage: 229
Endpage: 236
Year of Publication: 2021
Title of the Conference: ISMIR 2021
Place of the conference: Online
Publikation type: Conference Paper
Abstract: This paper uses the emerging provision of human harmonic analyses to assess how reliably we can map from knowing only when chords and keys change to a full identification of what those chords and keys are. We do this with a simple implementation of pitch class profile matching methods, partly to provide a benchmark score against which to judge the performance of less readily interpretable machine learning systems, many of which explicitly separate these when and what tasks and provide performance evaluation for these separate stages. Additionally, as this ‘oracle’-style, ‘perfect’ segmentation information will not usually be available in practice, we test the sensitivity of these methods to slight modifications in the position of segment boundaries by introducing deliberate errors. This study examines several corpora. The focus on is symbolic data, though we include one audio dataset for comparison. The code and corpora (of symbolic scores and analyses) are available within:
URL of the first publication:
Link to this record: hdl:20.500.11880/32057
ISBN: 978-1-7327299-0-2
Date of registration: 16-Dec-2021
Faculty: P - Philosophische Fakultät
Department: P - Musikwissenschaft
Professorship: P - Prof. Dr. Rainer Kleinertz
Collections:SciDok - Der Wissenschaftsserver der Universität des Saarlandes

Files for this record:
There are no files associated with this item.

Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.