The Fusion of Musical Traditions and Technology: A Systematic Literature Review of Artificial Intelligence in Music Education within Non-Western Contexts and Its Implications for Thai Music

Abstract

The application of artificial intelligence (AI) in music education has expanded rapidly over the past decade, particularly through the adoption of machine learning, deep learning, and generative artificial intelligence technologies for music creation, audio analysis, and the development of intelligent learning systems. Despite this growth, most existing studies have been conducted within Western musical contexts, where formal theoretical structures and standardized notation systems facilitate technological development and computational processing. In contrast, non-Western musical traditions, including Thai music, are characterized by oral transmission, experiential learning, master–disciple relationships, and strong cultural embeddedness. These distinctive characteristics create both opportunities and challenges for the integration of AI into music education. Consequently, there remains a significant need to synthesize existing knowledge regarding AI applications in non-Western music education and to explore their implications for preserving cultural identity and supporting meaningful learning processes. This study aimed to (1) synthesize existing knowledge on the application of artificial intelligence in non-Western music education, (2) examine the impacts of AI on musical identity and learning processes, and (3) develop a conceptual model for integrating artificial intelligence with Thai musical traditions within contemporary educational contexts.

This research employed a systematic literature review and knowledge synthesis approach following the PRISMA 2020 guidelines. The review process consisted of four major stages: identification, screening, eligibility assessment, and inclusion. These procedures were designed to ensure methodological transparency, systematic data collection, and replicability of findings. Literature searches were conducted through both international and national academic databases, including Scopus, Web of Science, Google Scholar, ThaiJO, and Thai Digital Collection. Boolean search operators such as AND, OR, and NOT were used to combine keywords related to artificial intelligence, music education, ethnomusicology, cultural heritage, non-Western music, and Thai music. The initial search yielded 360 documents. After removing duplicates, screening titles and abstracts, and evaluating full-text quality according to predetermined criteria, 60 documents were retained for final analysis. These consisted of 50 international studies and 10 studies specifically related to Thai contexts. All selected documents had undergone academic peer review and were further assessed using critical appraisal procedures and mixed-method quality assessment tools to ensure reliability, relevance, and methodological rigor before inclusion in the synthesis process.

Data were analyzed using thematic synthesis. The selected literature was categorized according to four research questions: (1) types of artificial intelligence technologies used in non-Western music education, (2) best practices for integrating AI into music education, (3) the impact of AI on musical identity, and (4) the influence of AI on learning processes. The analysis focused on identifying recurring themes, patterns, relationships, and emerging trends across the literature in order to construct a comprehensive understanding of the current state of knowledge.

The research findings revealed that artificial intelligence has been applied in music education through five major categories. First, AI is increasingly utilized for music creation and composition, particularly through generative systems capable of producing melodies, harmonies, rhythmic structures, and musical arrangements. Second, AI technologies are employed for audio analysis and signal processing, enabling automated transcription, pattern recognition, performance assessment, and music information retrieval. Third, intelligent tutoring systems and adaptive learning platforms provide personalized learning experiences, immediate feedback, and learner-centered instructional support. Fourth, AI contributes significantly to cultural heritage preservation through digital archiving, documentation, classification, and restoration of musical materials. Fifth, human–technology interaction systems facilitate collaborative engagement between learners, teachers, communities, and intelligent technologies in musical learning environments.

The findings further indicate that AI offers considerable potential for supporting personalized learning, expanding access to musical knowledge, providing real-time feedback, and enhancing educational efficiency. However, successful integration of AI into traditional music education requires careful consideration of cultural contexts, social learning processes, and indigenous knowledge systems. In the case of Thai music, the master–disciple tradition remains a fundamental mechanism for transmitting musical knowledge, values, performance practices, and cultural meanings. Although AI can support information delivery and skill development, it cannot fully replace the social interaction, cultural immersion, and human relationships that characterize traditional learning environments. Therefore, the implement-tation of AI in Thai music education should emphasize augmentation rather than replacement.

Based on the synthesis of all reviewed documents, this study developed the T-AIM Model, a conceptual framework designed to explain the integration of Thai musical traditions and artificial intelligence in contemporary learning environments. The model consists of four interrelated components: Tradition (T), Artificial Intelligence (A), Interaction (I), and Mediation (M). Tradition represents the cultural foundations, values, knowledge systems, and musical practices embedded within Thai music. Artificial Intelligence refers to technological tools and systems that support analysis, creativity, instruction, and knowledge management. Interaction emphasizes the social relationships among learners, teachers, communities, and technologies that facilitate collaborative learning and knowledge construction. Mediation highlights the role of AI as a cognitive and educational intermediary that connects traditional knowledge with emerging technological possibilities. The model proposes that AI should function as a supportive and enabling mechanism that strengthens learning opportunities while preserving cultural authenticity and social engagement.

The study contributes to the growing body of knowledge concerning culturally responsive applications of artificial intelligence in music education. It demonstrates that the integration of AI into non-Western musical traditions must be guided by principles of cultural sustainability, ethical responsibility, and respect for indigenous knowledge systems. The findings suggest that future technological development should balance innovation with cultural preservation to ensure that digital transformation does not undermine musical identity or disconnect music from its cultural context. Future research should focus on experimental studies that evaluate the effectiveness of the T-AIM Model in authentic educational settings, the development of AI technologies tailored specifically to Thai musical characteristics, and the establishment of ethical frameworks for managing musical data, particularly the preservation and use of recordings from master musicians. Such efforts will help ensure that the integration of artificial intelligence and traditional music can proceed in a balanced, culturally sensitive, and sustainable manner.