The Objective Ear: assessing the progress of a music task

• Main Authors: Joel Burrows, Vivekanandan Kumar
• Format: Article
• Language: English
• Published: SpringerOpen 2018-08-01
• Series: Smart Learning Environments
• Subjects: Music education; Assessment; Learning analytics; Machine learning
• Online Access: http://link.springer.com/article/10.1186/s40561-018-0062-1

Abstract Music educators must assess the progress made by their students between lessons. This assessment process is error prone, relying on memory and listening skills. The Objective Ear is a tool that takes as input a pair of performances of a piece of music and returns an accurate and reliable assessment of the progress between the performances. The tool evaluates performances using domain knowledge to generate a vector of metrics. The vectors for a pair of performances are subtracted from each other and the differences are used as input to a machine-learning classifier which maps the differences to an assessment. The implementation demonstrates that the Objective Ear tool is a feasible and practical solution to the problem of assessment. The assessments provided by this tool are valuable to students and teachers, but also to music education researchers who can use progress data to better model music education.