INTEGRATING AI-BASED ANALYSIS WITH INDIGENOUS PARADIGMS: A STUDY OF STRUCTURE AND MEANING IN ONYEE NWANKPA’S ANURUM OLU

Abstract

This study explores the intersection of artificial intelligence and Indigenous epistemologies in music analysis. Focusing on Anurum Olu, an Indigenous Igbo musical composition by Onyee Nwankpa, the research addresses a critical gap in AI‑based analysis of culturally grounded works. Although African music is widely acknowledged as a repository of epistemic and pedagogical knowledge, its structural and symbolic richness remains underexamined within computational frameworks. This study advances musicological discourse through decolonial and interdisciplinary methodologies. The research aims to (1) model the structural features of Anurum Olu using AI tools, (2) interpret its cultural and epistemic meanings through Indigenous paradigms, and (3) evaluate the compatibility of AI with Indigenous musical syntax. It asks: How effectively can an AI model the sonic features of Anurum Olu without compromising its epistemic integrity, and how do Indigenous theories enhance interpretation beyond AI’s reach? Three frameworks guide the study: Episto‑Musical Pedagogy Theory, Cultural Semiotics Theory, and Ethnomusicology Theory. Using a hybrid methodology that integrates computational analysis with interpretive coding grounded in Igbo cosmology, findings show that AI effectively modeled rhythmic and tonal structures, while Indigenous paradigms revealed deeper symbolic meanings. The hybrid approach strengthened interpretive fidelity and epistemic resonance. The study recommends expanding AI training datasets to include Indigenous musical logics, adopting co‑creation models with culture‑bearers, and institutionalizing hybrid analytical frameworks to safeguard epistemic integrity in future AI‑music research.