Granular Dance

Daniel Bisig

Granular Dance

Daniel Bisig

Research Centre for Dance Research

Zurich University of the Arts

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

59 Downloads (Pure)

Abstract

This publication presents a tool that can be trained with motion capture data and then used to generate new dance movement sequences. This tool combines two different components: a deep learning model based on a recurrent adversarial autoencoder architecture, and a sequence blending mechanism that is inspired by granular and concatenative sound synthesis techniques. The publication contextualizes this tool with respect to other artificial intelligence inspired approaches in dance. Subsequently, the implementation of the tool is detailed and results from its usage are presented. These results are discussed in terms of their artistic potential. Finally, the publication provides a brief outlook into possible future research directions.

Original language	English
Title of host publication	Proceedings of the 9th Conference on Computation, Communication, Aesthetics & X
Editors	Miguel Carvalhais, Mario Verdicchio, Luísa Ribas, André Rangel
Place of Publication	Portugal
Publisher	i2ADS
Pages	176-195
Number of pages	20
ISBN (Print)	978-989-9049-06-2
Publication status	Published - 12 Jul 2021
Event	Ninth Conference on Computation, Communication, Aesthetics & X - Online Duration: 12 Jul 2021 → 16 Jul 2021 Conference number: 9 https://www.designresearchsociety.org/events/9th-conference-on-computation-communication-aesthetics-x-online-event

Publication series

Name	Proceedings of xCoAx International conference on Computation, Communication, Aesthetics & X
ISSN (Print)	2183-9069

Conference

Conference	Ninth Conference on Computation, Communication, Aesthetics & X
Abbreviated title	xCoAx
Period	12/07/21 → 16/07/21
Internet address	https://www.designresearchsociety.org/events/9th-conference-on-computation-communication-aesthetics-x-online-event

Keywords

Generative Art
Dance
Artificial Intelligence
Machine Learning
Granular Synthesis
Concatenative Synthesis

Access to Document

xCoAx2021-BisigFinal published version, 1 MB

1 Conference proceeding

Strings P
Bisig, D., Wegner, E. & Kimmig, H., 12 Jul 2021, Proceedings of the 9th Conference on Computation, Communication, Aesthetics & X. Carvalhais, M., Verdicchio, M., Ribas, L. & Rangel, A. (eds.). Portugal: i2ADS, p. 546-553 8 p. (Proceedings of xCoAx International conference on Computation, Communication, Aesthetics & X).
Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

Open Access

Cite this

Granular Dance. / Bisig, Daniel.
Proceedings of the 9th Conference on Computation, Communication, Aesthetics & X. ed. / Miguel Carvalhais; Mario Verdicchio; Luísa Ribas; André Rangel. Portugal: i2ADS, 2021. p. 176-195 (Proceedings of xCoAx International conference on Computation, Communication, Aesthetics & X).

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

Bisig, D 2021, Granular Dance. in M Carvalhais, M Verdicchio, L Ribas & A Rangel (eds), Proceedings of the 9th Conference on Computation, Communication, Aesthetics & X. Proceedings of xCoAx International conference on Computation, Communication, Aesthetics & X, i2ADS, Portugal, pp. 176-195, Ninth Conference on Computation, Communication, Aesthetics & X, 12/07/21.

@inproceedings{9c3d136f4eac4c5aa89559274b0ba56e,

title = "Granular Dance",

abstract = "This publication presents a tool that can be trained with motion capture data and then used to generate new dance movement sequences. This tool combines two different components: a deep learning model based on a recurrent adversarial autoencoder architecture, and a sequence blending mechanism that is inspired by granular and concatenative sound synthesis techniques. The publication contextualizes this tool with respect to other artificial intelligence inspired approaches in dance. Subsequently, the implementation of the tool is detailed and results from its usage are presented. These results are discussed in terms of their artistic potential. Finally, the publication provides a brief outlook into possible future research directions.",

keywords = "Generative Art, Dance, Artificial Intelligence, Machine Learning, Granular Synthesis, Concatenative Synthesis",

author = "Daniel Bisig",

year = "2021",

month = jul,

day = "12",

language = "English",

isbn = "978-989-9049-06-2",

series = "Proceedings of xCoAx International conference on Computation, Communication, Aesthetics & X",

publisher = "i2ADS",

pages = "176--195",

editor = "Carvalhais, {Miguel } and Verdicchio, {Mario } and Ribas, {Lu{\'i}sa } and Rangel, {Andr{\'e} }",

booktitle = "Proceedings of the 9th Conference on Computation, Communication, Aesthetics & X",

address = "Portugal",

note = "Ninth Conference on Computation, Communication, Aesthetics & X, xCoAx ; Conference date: 12-07-2021 Through 16-07-2021",

url = "https://www.designresearchsociety.org/events/9th-conference-on-computation-communication-aesthetics-x-online-event",

}

TY - GEN

T1 - Granular Dance

AU - Bisig, Daniel

N1 - Conference code: 9

PY - 2021/7/12

Y1 - 2021/7/12

N2 - This publication presents a tool that can be trained with motion capture data and then used to generate new dance movement sequences. This tool combines two different components: a deep learning model based on a recurrent adversarial autoencoder architecture, and a sequence blending mechanism that is inspired by granular and concatenative sound synthesis techniques. The publication contextualizes this tool with respect to other artificial intelligence inspired approaches in dance. Subsequently, the implementation of the tool is detailed and results from its usage are presented. These results are discussed in terms of their artistic potential. Finally, the publication provides a brief outlook into possible future research directions.

AB - This publication presents a tool that can be trained with motion capture data and then used to generate new dance movement sequences. This tool combines two different components: a deep learning model based on a recurrent adversarial autoencoder architecture, and a sequence blending mechanism that is inspired by granular and concatenative sound synthesis techniques. The publication contextualizes this tool with respect to other artificial intelligence inspired approaches in dance. Subsequently, the implementation of the tool is detailed and results from its usage are presented. These results are discussed in terms of their artistic potential. Finally, the publication provides a brief outlook into possible future research directions.

KW - Generative Art

KW - Dance

KW - Artificial Intelligence

KW - Machine Learning

KW - Granular Synthesis

KW - Concatenative Synthesis

M3 - Conference proceeding

SN - 978-989-9049-06-2

T3 - Proceedings of xCoAx International conference on Computation, Communication, Aesthetics & X

SP - 176

EP - 195

BT - Proceedings of the 9th Conference on Computation, Communication, Aesthetics & X

A2 - Carvalhais, Miguel

A2 - Verdicchio, Mario

A2 - Ribas, Luísa

A2 - Rangel, André

PB - i2ADS

CY - Portugal

T2 - Ninth Conference on Computation, Communication, Aesthetics & X

Y2 - 12 July 2021 through 16 July 2021

ER -

Granular Dance

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Research output

Strings P

Cite this