Gianluca Micchi
Not All Roads Lead to Rome: Pitch Representation and Model Architecture for Automatic Harmonic Analysis
Micchi, Gianluca; Gotham, Mark; Giraud, Mathieu
Abstract
Automatic harmonic analysis has been an enduring focus of the MIR community, and has enjoyed a particularly vigorous revival of interest in the machine-learning age. We focus here on the specific case of Roman numeral analysis which, by virtue of requiring key/functional information in addition to chords, may be viewed as an acutely challenging use case.
We report on three main developments. First, we provide a new meta-corpus bringing together all existing Roman numeral analysis datasets; this offers greater scale and diversity, not only of the music represented, but also of human analytical viewpoints. Second, we examine best practices in the encoding of pitch, time, and harmony for machine learning tasks. The main contribution here is the introduction of full pitch spelling to such a system, an absolute must for the comprehensive study of musical harmony. Third, we devised and tested several neural network architectures and compared their relative accuracy. In the best-performing of these models, convolutional layers gather the local information needed to analyse the chord at a given moment while a recurrent part learns longer-range harmonic progressions.
Altogether, our best representation and architecture produce a small but significant improvement on overall accuracy while simultaneously integrating full pitch spelling. This enables the system to retain important information from the musical sources and provide more meaningful predictions for any new input.
Journal Article Type | Article |
---|---|
Publication Date | 2020 |
Deposit Date | Feb 29, 2024 |
Journal | Transactions of the International Society for Music Information Retrieval |
Electronic ISSN | 2514-3298 |
Publisher | Ubiquity Press |
Peer Reviewed | Peer Reviewed |
Volume | 3 |
Pages | 42 – 54 |
DOI | https://doi.org/10.5334/tismir.45 |
Public URL | https://durham-repository.worktribe.com/output/2273249 |
Additional Information | This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). Available via https://doi.org/10.5334/tismir.45 |
You might also like
The “OpenScore String Quartet” Corpus
(2023)
Presentation / Conference Contribution
The 'Measure Map': An inter-operable standard for aligning symbolic music
(2023)
Presentation / Conference Contribution
Chromatic Chords in Theory and Practice
(2023)
Presentation / Conference Contribution
When in Rome: A Meta-corpus of Functional Harmony
(2023)
Journal Article
Musical Micro-Timing for Live Coding
(2023)
Presentation / Conference Contribution
Downloadable Citations
About Durham Research Online (DRO)
Administrator e-mail: dro.admin@durham.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search