AMPACT: Automatic Music Performance Analysis and Comparison Toolkit

FAIN: HAA-281007-21

CUNY Research Foundation, Brooklyn College (Brooklyn, NY 11210-2850)
Johanna Catriona Devaney (Project Director: January 2021 to present)

A suite of tools to enable the computational analysis of musical performances. 

This project proposes to further develop a suite of automatic software tools for quantitatively analyzing musical performances for which a corresponding musical score is available, entitled the Automatic Music Performance Analysis and Comparison Toolkit (AMPACT). Musical performance is an interesting focus of study because, unlike musical scores, a traditional object of study, the performance is what listeners actually hear. A musical performance can convey both the musicians’ interpretation of the written score as well as emphasize, or even manipulate, the emotional content of the music through small variations in timing, dynamics, and tuning. Historically, studies of recorded musical performance have made use of manual techniques, but their laboriousness limited the number of performances that could be studied and the observations that could be made. The automatic tools provided by AMPACT facilitate much larger-scale investigations than are possible with manual annotation methods.