Software-based computational music analysis tools have become ubiquitous, and enable scholars to explore music in new ways. These frameworks allow us to investigate how musical features relate to mode in Renaissance compositions. One problem arising is how to computationally determine the mode of a composition. Current key finding algorithms can find the key of a common practice period composition with a certain degree of accuracy, but cannot be used to determine mode in Renaissance music. Another problem is the differing number of mode definitions among Renaissance, and contemporary scholars. The solution lies in developing a machine-learning based mode-finding system, adaptable to different types of mode definitions.
Feature extraction in machine learning, pattern recognition, and image processing involves establishing an initial set of (music analysis) data, and building derived informative data. A careful selection and tested set of features assists in learning or generalizing steps, and can lead to our better understanding of use of mode in Renaissance music.
Reiner Krämer is a teacher, music theorist, composer, programmer, or in short, a music algorist. He earned a Ph.D. in music theory with a related field in computer music at the University of North Texas (UNT). His research interests include computational music analysis, computer music, popular music, counterpoint, and compositional theory.
Reiner works as a Postdoctoral Researcher at McGill University in Montréal, Canada, where he leads an interdisciplinary team of doctoral, master’s, and undergraduate students. Reiner is a member of the Centre for Interdisciplinary Research in Music Media and Technology (CIRMMT), and teaches an online course of Rock Music History at Metropolitan State University of Denver.