Battle Rap as a Framework for Human-Machine Co-Creation

Olatunji, Ibukun; Sheppard, Matt; Jones, Matt; Rahat, Alma; Rogers, Amanda

doi:https://doi.org/

Conference Paper/Proceeding/Abstract 264 views 21 downloads

Battle Rap as a Framework for Human-Machine Co-Creation

Ibukun Olatunji, Matt Sheppard, Matt Jones

, Alma Rahat, Amanda Rogers

ICCC 2025 Proceedings of the Sixteenth International Conference on Computational Creativity

Swansea University Authors: Matt Jones , Alma Rahat, Amanda Rogers

PDF | Version of Record

Published under a Creative Commons Attribution (CC BY) license.
Download (697.75KB)

Check full text

Abstract

We present a human-in-the-loop GAN framework for battle rap, where a human artist (MC) serves as generator, and the AI acts as an adaptive discriminator. The AI provides feedback on rhyme complexity, coherence, and stylistic alignment, challenging the MC’s improvisational skill. Fine-tuned language...

Full description

Published in:	ICCC 2025 Proceedings of the Sixteenth International Conference on Computational Creativity
ISBN:	978-989-54160-7-3
ISSN:	3051-6706
Published:	State University of Campinas (Unicamp) Brazil Association for Computational Creativity (ACC) 2025
Online Access:	Check full text
URI:	https://cronfa.swan.ac.uk/Record/cronfa71550

first_indexed	2026-03-04T15:27:16Z
last_indexed	2026-04-29T05:27:00Z
id	cronfa71550
recordtype	SURis
fullrecord	<?xml version="1.0"?><rfc1807><datestamp>2026-04-28T11:59:50.0808370</datestamp><bib-version>v2</bib-version><id>71550</id><entry>2026-03-04</entry><title>Battle Rap as a Framework for Human-Machine Co-Creation</title><swanseaauthors><author><sid>10b46d7843c2ba53d116ca2ed9abb56e</sid><ORCID>0000-0001-7657-7373</ORCID><firstname>Matt</firstname><surname>Jones</surname><name>Matt Jones</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>6206f027aca1e3a5ff6b8cd224248bc2</sid><ORCID/><firstname>Alma</firstname><surname>Rahat</surname><name>Alma Rahat</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>5ddde1ecc99923098fd92c797ee0020b</sid><ORCID>0000-0002-0454-8183</ORCID><firstname>Amanda</firstname><surname>Rogers</surname><name>Amanda Rogers</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2026-03-04</date><deptcode>MACS</deptcode><abstract>We present a human-in-the-loop GAN framework for battle rap, where a human artist (MC) serves as generator, and the AI acts as an adaptive discriminator. The AI provides feedback on rhyme complexity, coherence, and stylistic alignment, challenging the MC’s improvisational skill. Fine-tuned language models emulate diverse rap styles, while voice cloning creates adversarial loops: the MC competesagainst stylised versions of their own voice in a dynamic, selfreflective duel. The system follows a dual-phase process: (i) an Emulation Phase, where AI mimics established flows to reinforce technical mastery, and (ii) an Improvisation Phase, where AI disrupts expectations to prompt originality. This ensures that creative growth emerges from constraint and challenge. Success is judged through MC evaluations of the AI’s performance as an adversary. Framed as a study paper, this work offers a thought experiment in adversarial co-creativity, modelling how AI might inspire, rather than merely assist, human expression. Beyond computational modelling, the framework offers insights into machine-mediated creativityand how AI can be designed to provoke human creativity through improvisation, challenge, and real-time performance. The study positions the AI as a dynamic co-performer capable of eliciting novel artistic responses. As such, it contributes to emerging discourse on creative AI systems that influence, not just assist, human expression</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>ICCC 2025 Proceedings of the Sixteenth International Conference on Computational Creativity</journal><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher>Association for Computational Creativity (ACC)</publisher><placeOfPublication>State University of Campinas (Unicamp) Brazil</placeOfPublication><isbnPrint>978-989-54160-7-3</isbnPrint><isbnElectronic/><issnPrint>3051-6706</issnPrint><issnElectronic/><keywords/><publishedDay>1</publishedDay><publishedMonth>8</publishedMonth><publishedYear>2025</publishedYear><publishedDate>2025-08-01</publishedDate><doi/><url>https://computationalcreativity.net/iccc25/proceedings/</url><notes/><college>COLLEGE NANME</college><department>Mathematics and Computer Science School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MACS</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>EPSRC studentship</funders><projectreference/><lastEdited>2026-04-28T11:59:50.0808370</lastEdited><Created>2026-03-04T15:18:30.2175171</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Biosciences, Geography and Physics - Geography</level></path><authors><author><firstname>Ibukun</firstname><surname>Olatunji</surname><order>1</order></author><author><firstname>Matt</firstname><surname>Sheppard</surname><order>2</order></author><author><firstname>Matt</firstname><surname>Jones</surname><orcid>0000-0001-7657-7373</orcid><order>3</order></author><author><firstname>Alma</firstname><surname>Rahat</surname><orcid/><order>4</order></author><author><firstname>Amanda</firstname><surname>Rogers</surname><orcid>0000-0002-0454-8183</orcid><order>5</order></author></authors><documents><document><filename>71550__36624__48aa41c47bb4470d8fedb459bb251fc3.pdf</filename><originalFilename>71550.VoR.pdf</originalFilename><uploaded>2026-04-28T11:57:13.9394590</uploaded><type>Output</type><contentLength>714494</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>Published under a Creative Commons Attribution (CC BY) license.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling	2026-04-28T11:59:50.0808370 v2 71550 2026-03-04 Battle Rap as a Framework for Human-Machine Co-Creation 10b46d7843c2ba53d116ca2ed9abb56e 0000-0001-7657-7373 Matt Jones Matt Jones true false 6206f027aca1e3a5ff6b8cd224248bc2 Alma Rahat Alma Rahat true false 5ddde1ecc99923098fd92c797ee0020b 0000-0002-0454-8183 Amanda Rogers Amanda Rogers true false 2026-03-04 MACS We present a human-in-the-loop GAN framework for battle rap, where a human artist (MC) serves as generator, and the AI acts as an adaptive discriminator. The AI provides feedback on rhyme complexity, coherence, and stylistic alignment, challenging the MC’s improvisational skill. Fine-tuned language models emulate diverse rap styles, while voice cloning creates adversarial loops: the MC competesagainst stylised versions of their own voice in a dynamic, selfreflective duel. The system follows a dual-phase process: (i) an Emulation Phase, where AI mimics established flows to reinforce technical mastery, and (ii) an Improvisation Phase, where AI disrupts expectations to prompt originality. This ensures that creative growth emerges from constraint and challenge. Success is judged through MC evaluations of the AI’s performance as an adversary. Framed as a study paper, this work offers a thought experiment in adversarial co-creativity, modelling how AI might inspire, rather than merely assist, human expression. Beyond computational modelling, the framework offers insights into machine-mediated creativityand how AI can be designed to provoke human creativity through improvisation, challenge, and real-time performance. The study positions the AI as a dynamic co-performer capable of eliciting novel artistic responses. As such, it contributes to emerging discourse on creative AI systems that influence, not just assist, human expression Conference Paper/Proceeding/Abstract ICCC 2025 Proceedings of the Sixteenth International Conference on Computational Creativity Association for Computational Creativity (ACC) State University of Campinas (Unicamp) Brazil 978-989-54160-7-3 3051-6706 1 8 2025 2025-08-01 https://computationalcreativity.net/iccc25/proceedings/ COLLEGE NANME Mathematics and Computer Science School COLLEGE CODE MACS Swansea University EPSRC studentship 2026-04-28T11:59:50.0808370 2026-03-04T15:18:30.2175171 Faculty of Science and Engineering School of Biosciences, Geography and Physics - Geography Ibukun Olatunji 1 Matt Sheppard 2 Matt Jones 0000-0001-7657-7373 3 Alma Rahat 4 Amanda Rogers 0000-0002-0454-8183 5 71550__36624__48aa41c47bb4470d8fedb459bb251fc3.pdf 71550.VoR.pdf 2026-04-28T11:57:13.9394590 Output 714494 application/pdf Version of Record true Published under a Creative Commons Attribution (CC BY) license. true eng https://creativecommons.org/licenses/by/4.0/
title	Battle Rap as a Framework for Human-Machine Co-Creation
spellingShingle	Battle Rap as a Framework for Human-Machine Co-Creation Matt Jones Alma Rahat Amanda Rogers
title_short	Battle Rap as a Framework for Human-Machine Co-Creation
title_full	Battle Rap as a Framework for Human-Machine Co-Creation
title_fullStr	Battle Rap as a Framework for Human-Machine Co-Creation
title_full_unstemmed	Battle Rap as a Framework for Human-Machine Co-Creation
title_sort	Battle Rap as a Framework for Human-Machine Co-Creation
author_id_str_mv	10b46d7843c2ba53d116ca2ed9abb56e 6206f027aca1e3a5ff6b8cd224248bc2 5ddde1ecc99923098fd92c797ee0020b
author_id_fullname_str_mv	10b46d7843c2ba53d116ca2ed9abb56e_*_Matt Jones 6206f027aca1e3a5ff6b8cd224248bc2__Alma Rahat 5ddde1ecc99923098fd92c797ee0020b_**_Amanda Rogers
author	Matt Jones Alma Rahat Amanda Rogers
author2	Ibukun Olatunji Matt Sheppard Matt Jones Alma Rahat Amanda Rogers
format	Conference Paper/Proceeding/Abstract
container_title	ICCC 2025 Proceedings of the Sixteenth International Conference on Computational Creativity
publishDate	2025
institution	Swansea University
isbn	978-989-54160-7-3
issn	3051-6706
publisher	Association for Computational Creativity (ACC)
college_str	Faculty of Science and Engineering
hierarchytype
hierarchy_top_id	facultyofscienceandengineering
hierarchy_top_title	Faculty of Science and Engineering
hierarchy_parent_id	facultyofscienceandengineering
hierarchy_parent_title	Faculty of Science and Engineering
department_str	School of Biosciences, Geography and Physics - Geography{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Biosciences, Geography and Physics - Geography
url	https://computationalcreativity.net/iccc25/proceedings/
document_store_str	1
active_str	0
description	We present a human-in-the-loop GAN framework for battle rap, where a human artist (MC) serves as generator, and the AI acts as an adaptive discriminator. The AI provides feedback on rhyme complexity, coherence, and stylistic alignment, challenging the MC’s improvisational skill. Fine-tuned language models emulate diverse rap styles, while voice cloning creates adversarial loops: the MC competesagainst stylised versions of their own voice in a dynamic, selfreflective duel. The system follows a dual-phase process: (i) an Emulation Phase, where AI mimics established flows to reinforce technical mastery, and (ii) an Improvisation Phase, where AI disrupts expectations to prompt originality. This ensures that creative growth emerges from constraint and challenge. Success is judged through MC evaluations of the AI’s performance as an adversary. Framed as a study paper, this work offers a thought experiment in adversarial co-creativity, modelling how AI might inspire, rather than merely assist, human expression. Beyond computational modelling, the framework offers insights into machine-mediated creativityand how AI can be designed to provoke human creativity through improvisation, challenge, and real-time performance. The study positions the AI as a dynamic co-performer capable of eliciting novel artistic responses. As such, it contributes to emerging discourse on creative AI systems that influence, not just assist, human expression
published_date	2025-08-01T07:53:49Z
_version_	1866051754086367232
score	10.995519

Battle Rap as a Framework for Human-Machine Co-Creation

Similar Items