Digital Technology-Driven Music Teaching Model Innovation and Students’ Artistic Literacy Enhancement

Abstract

Abstract This study examines the use of digital technologies in music teaching, focusing on the combination of musical feature extraction, attention mechanisms, and convolutional neural networks, and the potential impact of these technologies on improving students’ artistic literacy. The study explores digital technology-driven innovations in music teaching models and their impact on improving students’ artistic literacy. The study preprocesses musical features and uses Mel’s inverted spectral coefficients to extract key audio features. The feature extraction process is further optimized by introducing the attention mechanism and convolutional neural network to ensure the effectiveness and relevance of the music teaching content. On this basis, a music teaching aid platform is designed, which concentrates on resource sharing, openness and professionalism. Through questionnaire surveys and empirical analysis, this study conducted an in-depth analysis of the platform’s willingness to use, online learning behavior, and system performance. The results show that relative advantage, perceived quality and perceived usefulness are the main factors affecting the willingness to use. Meanwhile, there are significant differences in task participation behavior among students of different genders. The system performance test shows that the platform can effectively support multi-user concurrent operation and meet music teaching needs. To summarize, the study proves the potential of digital technology in enhancing the effectiveness of music teaching and students’ artistic literacy. It provides a valuable reference for the future application of educational technology.