AI-terity 2.0: An Autonomous NIME Featuring GANSpaceSynth Deep Learning Model

Koray Tahiroğlu; Miranda Kastemaa; Oskar Koli

doi:10.21428/92fbeb44.3d0e9e12

AI-terity 2.0: An Autonomous NIME Featuring GANSpaceSynth Deep Learning Model

Koray Tahiroğlu, Miranda Kastemaa, Oskar Koli

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

8 Downloads (Pure)

Abstract

In this paper we present the recent developments in the AI-terity instrument. AI-terity is a deformable, non-rigid musical instrument that comprises a particular artificial intelligence (AI) method for generating audio samples for real-time audio synthesis. As an improvement, we developed the control interface structure with additional sensor hardware. In addition, we implemented a new hybrid deep learning architecture, GANSpaceSynth, in which we applied the GANSpace method on the GANSynth model. Following the deep learning model improvement, we developed new autonomous features for the instrument that aim at keeping the musician in an active and uncertain state of exploration. Through these new features, the instrument enables more accurate control on GAN latent space. Further, we intend to investigate the current developments through a musical composition that idiomatically reflects the new autonomous features of the AI-terity instrument. We argue that the present technology of AI is suitable for enabling alternative autonomous features in audio domain for the creative practices of musicians.

Original language	English
Title of host publication	Proceedings of the International Conference on New Interfaces for Musical Expression
Publisher	International Conference on New Interfaces for Musical Expression
Volume	2021
DOIs	https://doi.org/10.21428/92fbeb44.3d0e9e12
Publication status	Published - 15 Jun 2021
MoE publication type	A4 Article in a conference publication
Event	International Conference on New Interfaces for Musical Expression - Shanghai, China Duration: 15 Jun 2021 → 18 Jun 2021 http://nime2021.org/

Publication series

Name
ISSN (Electronic)	2220-4806

Conference

Conference	International Conference on New Interfaces for Musical Expression
Abbreviated title	NIME
Country/Territory	China
City	Shanghai
Period	15/06/2021 → 18/06/2021
Internet address	http://nime2021.org/

Keywords

Artificial Intelligence (AI)
new interfaces for musical expression
Digital musical instruments
Deep Learning
GAN
GANSpaceSynth
SOPI
NIME

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.21428/92fbeb44.3d0e9e12Licence: CC BY

AI-terity 2.0Final published version, 3 MBLicence: CC BY

OpenUrl availability

Full text

Cite this

@inproceedings{c958eed23db54b7796515e50ade183ef,

title = "AI-terity 2.0: An Autonomous NIME Featuring GANSpaceSynth Deep Learning Model",

abstract = "In this paper we present the recent developments in the AI-terity instrument. AI-terity is a deformable, non-rigid musical instrument that comprises a particular artificial intelligence (AI) method for generating audio samples for real-time audio synthesis. As an improvement, we developed the control interface structure with additional sensor hardware. In addition, we implemented a new hybrid deep learning architecture, GANSpaceSynth, in which we applied the GANSpace method on the GANSynth model. Following the deep learning model improvement, we developed new autonomous features for the instrument that aim at keeping the musician in an active and uncertain state of exploration. Through these new features, the instrument enables more accurate control on GAN latent space. Further, we intend to investigate the current developments through a musical composition that idiomatically reflects the new autonomous features of the AI-terity instrument. We argue that the present technology of AI is suitable for enabling alternative autonomous features in audio domain for the creative practices of musicians.",

keywords = "Artificial Intelligence (AI), new interfaces for musical expression, Digital musical instruments, Deep Learning, GAN, GANSpaceSynth, SOPI, NIME",

author = "Koray Tahiroğlu and Miranda Kastemaa and Oskar Koli",

year = "2021",

month = jun,

day = "15",

doi = "10.21428/92fbeb44.3d0e9e12",

language = "English",

volume = "2021",

publisher = "International Conference on New Interfaces for Musical Expression",

booktitle = "Proceedings of the International Conference on New Interfaces for Musical Expression",

note = "International Conference on New Interfaces for Musical Expression, NIME ; Conference date: 15-06-2021 Through 18-06-2021",

url = "http://nime2021.org/",

}

Tahiroğlu, K, Kastemaa, M & Koli, O 2021, AI-terity 2.0: An Autonomous NIME Featuring GANSpaceSynth Deep Learning Model. in Proceedings of the International Conference on New Interfaces for Musical Expression. vol. 2021, International Conference on New Interfaces for Musical Expression, International Conference on New Interfaces for Musical Expression, Shanghai, China, 15/06/2021. https://doi.org/10.21428/92fbeb44.3d0e9e12

AI-terity 2.0: An Autonomous NIME Featuring GANSpaceSynth Deep Learning Model. / Tahiroğlu, Koray; Kastemaa, Miranda; Koli, Oskar.
Proceedings of the International Conference on New Interfaces for Musical Expression. Vol. 2021 International Conference on New Interfaces for Musical Expression, 2021.

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

TY - GEN

T1 - AI-terity 2.0: An Autonomous NIME Featuring GANSpaceSynth Deep Learning Model

AU - Tahiroğlu, Koray

AU - Kastemaa, Miranda

AU - Koli, Oskar

PY - 2021/6/15

Y1 - 2021/6/15

N2 - In this paper we present the recent developments in the AI-terity instrument. AI-terity is a deformable, non-rigid musical instrument that comprises a particular artificial intelligence (AI) method for generating audio samples for real-time audio synthesis. As an improvement, we developed the control interface structure with additional sensor hardware. In addition, we implemented a new hybrid deep learning architecture, GANSpaceSynth, in which we applied the GANSpace method on the GANSynth model. Following the deep learning model improvement, we developed new autonomous features for the instrument that aim at keeping the musician in an active and uncertain state of exploration. Through these new features, the instrument enables more accurate control on GAN latent space. Further, we intend to investigate the current developments through a musical composition that idiomatically reflects the new autonomous features of the AI-terity instrument. We argue that the present technology of AI is suitable for enabling alternative autonomous features in audio domain for the creative practices of musicians.

AB - In this paper we present the recent developments in the AI-terity instrument. AI-terity is a deformable, non-rigid musical instrument that comprises a particular artificial intelligence (AI) method for generating audio samples for real-time audio synthesis. As an improvement, we developed the control interface structure with additional sensor hardware. In addition, we implemented a new hybrid deep learning architecture, GANSpaceSynth, in which we applied the GANSpace method on the GANSynth model. Following the deep learning model improvement, we developed new autonomous features for the instrument that aim at keeping the musician in an active and uncertain state of exploration. Through these new features, the instrument enables more accurate control on GAN latent space. Further, we intend to investigate the current developments through a musical composition that idiomatically reflects the new autonomous features of the AI-terity instrument. We argue that the present technology of AI is suitable for enabling alternative autonomous features in audio domain for the creative practices of musicians.

KW - Artificial Intelligence (AI)

KW - new interfaces for musical expression

KW - Digital musical instruments

KW - Deep Learning

KW - GAN

KW - GANSpaceSynth

KW - SOPI

KW - NIME

UR - https://nime.pubpub.org/pub/9zu49nu5/release/1?readingCollection=71dd0131

U2 - 10.21428/92fbeb44.3d0e9e12

DO - 10.21428/92fbeb44.3d0e9e12

M3 - Conference contribution

VL - 2021

BT - Proceedings of the International Conference on New Interfaces for Musical Expression

PB - International Conference on New Interfaces for Musical Expression

T2 - International Conference on New Interfaces for Musical Expression

Y2 - 15 June 2021 through 18 June 2021

ER -

AI-terity 2.0: An Autonomous NIME Featuring GANSpaceSynth Deep Learning Model

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

OpenUrl availability

Other files and links

Fingerprint

digitalmusicalinteractions: Digital Musical Interactions 2

Technoscientific Practices of Music

Communal; AI as a Material, Instrument and the Other

Cite this

AI-terity 2.0: An Autonomous NIME Featuring GANSpaceSynth Deep Learning Model

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

OpenUrl availability

Other files and links

Fingerprint

Projects

digitalmusicalinteractions: Digital Musical Interactions 2

Activities

Technoscientific Practices of Music

Communal; AI as a Material, Instrument and the Other

Cite this