979-8-3315-3297-0/25/$31.00 ©2025 IEEE
An AI-Driven Workflow for Preserving Traditional
Malay Music Videos: A Case Study in Cultural
Heritage Enhancement
*Note: Sub-titles are not captured in Xplore and should not be used
M.Izani
Applied Media Department
Higher Colleges of Technology
Abu Dhabi, UAE
mohamadizanizainal@gmail.com
K. Trinh
Applied Media Department
Higher Colleges of Technology
Abu Dhabi, UAE
ktrinh@hct.ac.ae
M. Gabr
Applied Media Department
Higher Colleges of Technology
Abu Dhabi, UAE
mgabr@hct.ac.ae
A. Kaleel
Applied Media Department
Higher Colleges of Technology
Abu Dhabi, UAE
akaleel@hct.ac.ae
H. Harumaini
Sultan Salahuddin Abdul Aziz Shah
Polytechnic
Selangor, Malaysia
hazlina@psa.edu.my
A. Assad
Applied Media Department
Higher Colleges of Technology
Abu Dhabi, UAE
aali3@hct.ac.ae
Abstract— Preserving cultural heritage like traditional arts
and traditional music becomes increasingly challenging during
the digital age. We presented a workflow that uses generative AI
to preserve traditional Malay music in video format with an
emphasis on cultural integrity through photorealistic video
generation. Our enhanced framework uses Low-Rank
Adaptation (LoRA) combined with Splitter.ai-based vocal
isolation and Kling.ai motion synchronization along with other
artificial intelligence techniques to completely process and
enhance audiovisual elements. We started our research design
by deploying generative AI tools throughout a production
process starting from concept development, facial synthesis, and
training alongside motion-lip synchronization before post-
production to ensure visual harmony without sacrificing
storytelling elements and technical precision. The workflow
consists of expert validation points, loop refinement linked to
cultural accuracy loss, and computational performance. The
end results show that generative AI techniques create successful
links between traditional artistic forms with the present
multimedia formats to preserve traditional Malay music. This
research introduces a workflow that allows reproducible AI-
assisted preservation methods which give opportunities to
heritage experts and authorities helpful guidance to integrate
technical innovations with cultural integrity.
Keywords—Artificial Intelligence, Cultural Heritage, AI-
Driven Video Production, LoRA Face Cloning, AI Audio
Processing, Motion Synchronization, Intangible Cultural
Heritage (ICH)
I. INTRODUCTION
The attention on intangible cultural heritage preservation
has grown in recent years because traditional arts face
vulnerability alongside cultural dangers [1]. Traditional music
is one of the arts that faces high risks of disappearance when
globalization affects how people consume media because this
music media is closely linked to people's heritage and
community traditions [2]. The integration of artificial
intelligence (AI) technology has become a promising
approach for cultural preservation because of existing issues
in the field [3]. Implementing generative AI for traditional
audiovisual materials is very challenging and difficult because
they need precise execution alignment as well as accurate
cultural authenticity and thematic coherence [4]. The existing
literature examines immersive video [5], facial animation [6],
or generative image synthesis [7] independently while failing
to develop an integrated system that verifies cultural content
and narrative coherence. The proposed workflow presents a
complete AI process to transform traditional Malay music
videos while preserving cultural heritage while defining clear
narrative structures. This method uses the generative tools
Tensor for face cloning together with Splitter.ai for audio
track separation and Kling.ai for motion and lip-sync
alignment while Adobe Premiere Pro’s AI-enhanced editing
suite delivers the complete workflow that avoids new data
collection processes. The final framework verifies visual-
musical match while embracing Malay heritage themes to
provide adjustable representations of this intangible cultural
expression. Our workflow deploys artificial intelligence
processes to preserve traditional Malay music artifacts
through face cloning technology followed by motion-lip
synchronization and audio-visual compositing methods in
order to generate effective cultural restorations. The
evaluation system combines expert judges with precision
synchronization measurements to create an evidence-based
method for determining cultural accuracy during AI-assisted
conservation processes. The presented methodology creates
digital heritage preservation methods which are easily
repeatable with cultural sensitivity. This study builds a
potential benchmark for future AI-based ICH revitalization
research by integrating AI technologies into an integrated
process. The research model would benefit different
stakeholders including practitioners, policymakers and local
communities through its validated framework to preserve
traditional cultural expressions.
II. LITERATURE REVIEW
Intangible cultural heritage (ICH) encompassing oral
traditions, performing arts, and indigenous knowledge
underpins community identity across the globe [8, 9]. Yet,
unlike material artifacts, ICH remains vulnerable to erosion in
an increasingly globalized media environment [10, 11].
UNESCO’s Convention for the Safeguarding of the Intangible
Cultural Heritage has propelled preservation initiatives by
promoting systematic documentation and intergenerational
2025 5th International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET) | 979-8-3315-3297-0/25/$31.00 ©2025 IEEE | DOI: 10.1109/IRASET64571.2025.11008319
Authorized licensed use limited to: Higher College of Technology. Downloaded on June 02,2025 at 10:09:00 UTC from IEEE Xplore. Restrictions apply.