Xiaoquan Li
Siamese residual neural network for musical shape evaluation in piano performance assessment.
Li, Xiaoquan; Weiss, Stephan; Yan, Yijun; Li, Yinhe; Ren, Jinchang; Soraghan, John; Gong, Ming
Authors
Stephan Weiss
Dr Yijun Yan y.yan2@rgu.ac.uk
Research Fellow
YINHE LI y.li24@rgu.ac.uk
Research Student
Professor Jinchang Ren j.ren@rgu.ac.uk
Professor of Computing Science
John Soraghan
Ming Gong
Abstract
Understanding and identifying musical shape plays an important role in music education and performance assessment. To simplify the otherwise time- and cost-intensive musical shape evaluation, in this paper we explore how artificial intelligence (AI) driven models can be applied. Considering musical shape evaluation as a classification problem, a light-weight Siamese residual neural network (S-ResNN) is proposed to automatically identify musical shapes. To assess the proposed approach in the context of piano musical shape evaluation, we have generated a new dataset, namely MSED-4k, containing 4116 music pieces derived by 147 piano preparatory exercises and performed in 28 categories of musical shapes. The experimental results show that the S-ResNN significantly outperforms a number of benchmark methods in terms of the precision, recall and F1 score.
Citation
LI, X., WEISS, S., YAN, Y., LI, Y., REN, J., SORAGHAN, J. and GONG, M. 2023. Siamese residual neural network for musical shape evaluation in piano performance assessment. In Proceedings of the 31st European signal processing conference 2023 (EUSIPCO 2023), 4-8 September 2023, Helsinki, Finland. Piscataway: IEEE [online], pages 216-220. Available from: https://doi.org/10.23919/EUSIPCO58844.2023.10289901
| Presentation Conference Type | Conference Paper (published) |
|---|---|
| Conference Name | 31st European signal processing conference 2023 (EUSIPCO 2023) |
| Start Date | Sep 4, 2023 |
| End Date | Sep 8, 2023 |
| Acceptance Date | Nov 1, 2023 |
| Online Publication Date | Nov 1, 2023 |
| Publication Date | Dec 31, 2023 |
| Deposit Date | Dec 15, 2023 |
| Publicly Available Date | Dec 15, 2023 |
| Publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| Peer Reviewed | Peer Reviewed |
| Pages | 216-220 |
| Series Title | European signal processing conference (EUSIPCO) |
| Series ISSN | 2076-1465 |
| ISBN | 9789464593600 |
| DOI | https://doi.org/10.23919/EUSIPCO58844.2023.10289901 |
| Keywords | Piano performance assessment; Audio classification; Musical shape evaluation; Siamese network |
| Public URL | https://rgu-repository.worktribe.com/output/2174554 |
Files
LI 2023 Siamese residual neural network (AAM)
(704 Kb)
PDF
Copyright Statement
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
You might also like
Unsupervised change detection in hyperspectral images using principal components space data clustering.
(2022)
Presentation / Conference Contribution
Hyperspectral imagery quality assessment and band reconstruction using the Prophet model.
(2024)
Journal Article
Sparse autoencoder based hyperspectral anomaly detection with the singular spectrum analysis based spectral denoising.
(2024)
Presentation / Conference Contribution