Personalized Music Education: A Systematic Review of AI Generation Methods

Authors:
Open Access
Publisher website
Google Scholar
Abstract
Despite recent notable advances of AI-Education research, formal music education is still largely performed as it was at the beginning of the last century. Instrument technical practice especially is still largely performed in a classical setting with little use of modern technologies, possibly due to being a skill-based curriculum. While other researchers have argued for the potential benefits of using Artificial Intelligence for the personalization of music education, it still seems to be rare both in schools and in research. In this paper, we present a systematic literature review exploring the use of computational generation of exercises for personalized music learning, with a special interest in piano. To do so, we retrieve research papers that use AI to improve personalization in music education exploring both what computational methods can provide personalization in music teaching, and how frequently AI is actually used for generation in this context. We screened 360 papers retrieved from online repositories, selecting 40 relevant papers that would satisfy some minimal quality requirements. Analyzing the papers, we found that while there is interest from the scientific community in improving music education through AI and computational means more generally, AI is under-utilized for generation despite its potential for personalization. We found no examples of generation of piano technical exercises, and, more generally, that instrumental technique is indeed the aspect that has seen lesser use of AI enhancement, often limited to adding visualizations to normal instrumental practice.
Funding Information
  • European Commission (HORIZON-MSCA-2022-PF-01)
  • European Commission (101108690)

This publication has 46 references indexed in Scilit: