Bai Jiali

Zhaoqing University

Abstract：

As the core curriculum for musical auditory development, sight-singing and ear training has long been constrained by Western major-minor system methodologies, resulting in a structural deficiency in the integration of local musical language perception frameworks. Addressing the dual challenges of cultural silencing within indigenous music traditions and fragmented application of intelligent technologies, this study proposes a deep integration approach combining "cultural gene digitization" with "intelligent teaching scenarios." Grounded in computational ethnomusicology, the research extracts acoustic features and analyzes notation systems of representative musical genres from Guangfu, Chaoshan, and Hakka traditions, establishing a multidimensional "Lingnan Music Aesthetic Gene Bank" encompassing parameters such as tonal variation, rhythmic elasticity, and dialectal intonation patterns, while generating visualized knowledge maps. Building upon this foundation, the gene bank is systematically integrated into sight-singing training through digital-intelligent teaching platforms, creating a human-machine collaboration mechanism that combines "human instructors' cultural expertise with AI-driven skill acquisition." This forms a data-driven teaching cycle encompassing student assessment, context-specific immersive practice, and adaptive reinforcement. The study aims to provide a transferable paradigm for technological transformation of regional educational resources in higher music education, addressing the evolving disciplinary requirements of sight-singing and ear training in the digital age.

Key Words：

solfeggio; Lingnan musical heritage; aesthetic gene pool; computational ethnomusicology; AI-enhanced teaching