Towards Movement Generation with Audio Features

Benedikte Wallace; Charles Martin; Jim Torresen; Kristian Nymoen

doi:10.48550/arXiv.2011.13453

Towards Movement Generation with Audio Features

Benedikte Wallace, Charles Martin, Jim Torresen, Kristian Nymoen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Sound and movement are closely coupled, particularly in dance. Certain audio features have been found to affect the way we move to music. Is this relationship between sound and movement something which can be modelled using machine learning? This work presents initial experiments wherein high-level audio features calculated from a set of music pieces are included in a movement generation model trained on motion capture recordings of improvised dance. Our results indicate that the model learns to generate realistic dance movements which vary depending on the audio features.

Original language	English
Title of host publication	Proceedings of the 11th International Conference on Computational Creativity
Editors	F. Amlcar Cardoso, Penousal Machado, Tony Veale and Joao Miguel Cunha
Place of Publication	Coimbra, Portugal
Publisher	Association for Computational Creativity
Pages	284-287
ISBN (Print)	978-989-54160-2-8
DOIs	https://doi.org/10.48550/arXiv.2011.13453
Publication status	Published - 2020
Event	11th International Conference on Computational Creativity - Coimbra, Portugal Duration: 1 Jan 2020 → …

Conference

Conference	11th International Conference on Computational Creativity
Period	1/01/20 → …
Other	September 7-11

Access to Document

10.48550/arXiv.2011.13453

Cite this

@inproceedings{d5657a0ad0d846cf929f25ad3d610638,

title = "Towards Movement Generation with Audio Features",

abstract = "Sound and movement are closely coupled, particularly in dance. Certain audio features have been found to affect the way we move to music. Is this relationship between sound and movement something which can be modelled using machine learning? This work presents initial experiments wherein high-level audio features calculated from a set of music pieces are included in a movement generation model trained on motion capture recordings of improvised dance. Our results indicate that the model learns to generate realistic dance movements which vary depending on the audio features.",

author = "Benedikte Wallace and Charles Martin and Jim Torresen and Kristian Nymoen",

year = "2020",

doi = "10.48550/arXiv.2011.13453",

language = "English",

isbn = "978-989-54160-2-8",

pages = "284--287",

editor = "{F. Amlcar Cardoso, Penousal Machado, Tony Veale and Joao Miguel Cunha}",

booktitle = "Proceedings of the 11th International Conference on Computational Creativity",

publisher = "Association for Computational Creativity",

note = "11th International Conference on Computational Creativity ; Conference date: 01-01-2020",

}

Wallace, B, Martin, C, Torresen, J & Nymoen, K 2020, Towards Movement Generation with Audio Features. in FACPMTVAJMC (ed.), Proceedings of the 11th International Conference on Computational Creativity. Association for Computational Creativity, Coimbra, Portugal, pp. 284-287, 11th International Conference on Computational Creativity, 1/01/20. https://doi.org/10.48550/arXiv.2011.13453

Towards Movement Generation with Audio Features. / Wallace, Benedikte; Martin, Charles; Torresen, Jim et al.
Proceedings of the 11th International Conference on Computational Creativity. ed. / F. Amlcar Cardoso, Penousal Machado, Tony Veale and Joao Miguel Cunha. Coimbra, Portugal: Association for Computational Creativity, 2020. p. 284-287.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Towards Movement Generation with Audio Features

AU - Wallace, Benedikte

AU - Martin, Charles

AU - Torresen, Jim

AU - Nymoen, Kristian

PY - 2020

Y1 - 2020

N2 - Sound and movement are closely coupled, particularly in dance. Certain audio features have been found to affect the way we move to music. Is this relationship between sound and movement something which can be modelled using machine learning? This work presents initial experiments wherein high-level audio features calculated from a set of music pieces are included in a movement generation model trained on motion capture recordings of improvised dance. Our results indicate that the model learns to generate realistic dance movements which vary depending on the audio features.

AB - Sound and movement are closely coupled, particularly in dance. Certain audio features have been found to affect the way we move to music. Is this relationship between sound and movement something which can be modelled using machine learning? This work presents initial experiments wherein high-level audio features calculated from a set of music pieces are included in a movement generation model trained on motion capture recordings of improvised dance. Our results indicate that the model learns to generate realistic dance movements which vary depending on the audio features.

U2 - 10.48550/arXiv.2011.13453

DO - 10.48550/arXiv.2011.13453

M3 - Conference contribution

SN - 978-989-54160-2-8

SP - 284

EP - 287

BT - Proceedings of the 11th International Conference on Computational Creativity

A2 - null, F. Amlcar Cardoso, Penousal Machado, Tony Veale and Joao Miguel Cunha

PB - Association for Computational Creativity

CY - Coimbra, Portugal

T2 - 11th International Conference on Computational Creativity

Y2 - 1 January 2020

ER -

Towards Movement Generation with Audio Features

Abstract

Conference

Access to Document

Fingerprint

Cite this