Learning about Machine Learning with CRIM

Abstract

In this tutorial-essay I will consider how we can use machine learning, specifically dimensionality reduction and embedding methods, with the CRIM corpus. The guiding question is how style can be modeled quantitatively. Building both on music-theoretical conceptualization and machine learning techniques, it will be demonstrated that unsupervised clustering can serve to some degree as a proxy for stylistic similarity. The CRIM data set provides an ideal case study that will also point to some shortcomings of the computational methodology that can only be resolved by a critical view, drawing on musicological expertise and close-reading of sources.

Fabian C. Moss

Assistant Professor for Digital Music Philology and Music Theory

Fabian C. Moss is an assistant professor for Digital Music Philology and Music Theory at Julius-Maximilians University Würzburg (JMU), Germany.