Skip to main content

Research Repository

Advanced Search

Building an Embodied Musicking Dataset for co-creative music-making

Vear, Craig; Poltronieri, Fabrizio; Di Donato, Balandino; Zhang, Yawen; Benerradi, Johann; Hutchinson, Simon; Turowski, Paul; Shell, Jethro; Malekmohamadi, Hossein

Authors

Craig Vear

Fabrizio Poltronieri

Yawen Zhang

Johann Benerradi

Simon Hutchinson

Paul Turowski

Jethro Shell

Hossein Malekmohamadi



Abstract

In this paper, we present our findings of the design, development and deployment of a proof-of-concept dataset that captures some of the physiological, musicological, and psychological aspects of embodied musicking. After outlining the conceptual elements of this research, we explain the design of the dataset and the process of capturing the data. We then introduce two tests we used to evaluate the dataset: a) using data science techniques and b) a practice-based application in an AI-robot digital score. The results from these tests are conflicting: from a data science perspective the dataset could be considered garbage, but when applied to a real-world musicking situation performers reported it was transformative and felt to be ‘co-creative’. We discuss this duality and pose some important questions for future study. However, we feel that the datatset contains a set of relationships that are useful to explore in the creation of music.

Citation

Vear, C., Poltronieri, F., Di Donato, B., Zhang, Y., Benerradi, J., Hutchinson, S., Turowski, P., Shell, J., & Malekmohamadi, H. (2024, April). Building an Embodied Musicking Dataset for co-creative music-making. Presented at Evostar 2024: The Leading European Event on Bio‑Inspired Computation, Aberystwyth, Wales, United Kingdom

Presentation Conference Type Conference Paper (published)
Conference Name Evostar 2024: The Leading European Event on Bio‑Inspired Computation
Start Date Apr 3, 2024
End Date Apr 5, 2024
Online Publication Date Mar 29, 2024
Publication Date 2024
Deposit Date May 23, 2024
Publicly Available Date Mar 30, 2025
Publisher Springer
Peer Reviewed Peer Reviewed
Volume 14633
Pages 373-388
Series Title Lecture Notes in Computer Science
Series Number 14633
Series ISSN 0302-9743
Book Title Evostar 2024
ISBN 978-3-031-56991-3
DOI https://doi.org/10.1007/978-3-031-56992-0_24
Keywords dataset, music performance, embodied AI
Publisher URL https://www.springer.com/gp/computer-science/lncs

Files

This file is under embargo until Mar 30, 2025 due to copyright reasons.

Contact repository@napier.ac.uk to request a copy for personal use.







You might also like



Downloadable Citations