Exploring AI-Assisted Education Methods for Creating Traditional Vocal Music Content : Focusing on the Design of a 15-Week Pansori-Centered Course Plan
The Korean Society of Human and Nature · 30.07.2026 · 7 (2) · 189-230
DOI: 10.54913/hn.2026.7.2.189 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Korean Society of Human and Nature, online erschienen am 30.07.2026. Verfasst von Ye-jin Kim.
Abstract (Originalsprache)
This study aims to explore educational methods for creating traditional vocal music content using AI and to concretize them into an analytical framework and a 15-week course plan applicable to university-level education for traditional vocal music majors. Traditional vocal music education has long transmitted vocal timbre, breathing, rhythmic cycles, lyrics, and sigimsae through oral transmission and imitative learning. While this mode of education has played an important role in preserving the original form and stylistic identity of tradition, recent changes in the digital media environment and arts education require a new educational approach that enables learners to analyze the musical grammar of tradition and expand it into contemporary creative content. To this end, this study employs a qualitative research method centered on literature review and pedagogical design. It examines the characteristics of traditional vocal music education, the concept of creative traditional vocal music content, the educational possibilities of AI in music and gugak education, hybrid intelligence, and process-oriented assessment. Based on these discussions, the study identifies five components of creative traditional vocal music content: lyrics, rhythmic cycles, melody and sigimsae, vocal timbre and expression, and content media. It also classifies AI utilization into five functions: analysis, generation, visualization, editing, and reflection. By integrating these elements, the study proposes a cyclical framework consisting of “analysis of traditional vocal music elements-AI-based creative support-learner-centered reconstruction-content production-process-oriented reflection.” The central argument of this study is that AI should not be positioned as the subject of creation, but as an educational scaffold that supports learners’ analysis, reconstruction, production, and reflection. Generative AI can provide lyric drafts, creative ideas, content plans, visualization materials, and editing assistance. However, it cannot ultimately judge the vocal timbre, imyeon, rhythmic breathing, word-rhythm alignment, sigimsae, balim, and artistic completeness of traditional vocal music. Therefore, the key issue in AI-assisted traditional vocal music education is not what AI can generate, but whether learners can critically examine AI-generated results according to the musical grammar of traditional vocal music and reconstruct them through their own vocal expression and interpretation. This study presents pansori as the central case for applying the proposed framework. It suggests a process in which AI-generated results are critically reviewed, revised, and reconstructed according to the criteria of rhythmic cycles, word-rhythm alignment, imyeon, linguistic style, vocal timbre, and balim. On this basis, the study designs a 15-week course plan for university students majoring in traditional vocal music. The course consists of understanding creative traditional vocal music content and AI literacy, analyzing lyrics, rhythmic cycles, melody, sigimsae, and vocal timbre, experimenting with AI-assisted creation and prompt design, reconstructing creative works and producing content, and presenting, receiving feedback, and reflecting on the final outcome. The significance of this study lies in its proposal of an educational model that does not confine traditional vocal music education to transmission-centered practical training, but expands the musical grammar of tradition into contemporary creative content. By distinguishing the roles of AI and the instructor, this study emphasizes that the instructor’s professional judgment and learners’ creative subjectivity remain central in AI-assisted traditional vocal music education. However, this study is limited in that it does not empirically verify the educational effects of the proposed course plan through actual classroom implementation.
Zitieren
APA
Kim, Y. (2026). Exploring AI-Assisted Education Methods for Creating Traditional Vocal Music Content : Focusing on the Design of a 15-Week Pansori-Centered Course Plan. The Korean Society of Human and Nature, 7(2), 189-230. https://doi.org/10.54913/hn.2026.7.2.189
Vancouver
Kim Y. Exploring AI-Assisted Education Methods for Creating Traditional Vocal Music Content : Focusing on the Design of a 15-Week Pansori-Centered Course Plan. The Korean Society of Human and Nature. 2026;7(2):189-230. doi:10.54913/hn.2026.7.2.189
BibTeX
@article{Kim2026,
author = {Kim, Ye-jin},
title = {Exploring AI-Assisted Education Methods for Creating Traditional Vocal Music Content : Focusing on the Design of a 15-Week Pansori-Centered Course Plan},
journal = {The Korean Society of Human and Nature},
year = {2026},
volume = {7},
number = {2},
pages = {189--230},
doi = {10.54913/hn.2026.7.2.189}
}
EUVIMED