AES E-Library

AES E-Library

Scale Degree Profiles from Audio Investigated with Machine Learning

Document Thumbnail

In this paper we introduce and explore a method for extracting low dimensional features from digitized recordings of music performance: The so called constant Q scale degree profiles are 12-dimensional vectors that reflect the prominence of the 12 scale degrees in respective analyzed part of music. Here we study the type and amount of information that is captured in those profiles when calculated from whole short pieces of piano music. The analyzed data set includes pieces from Bach's Well-Tempered Clavier (WTC), part I and II, the sets of preludes that encompass a piece in every key by Chopin (op.28), Alkan (op.31), Scriabin (op.11), Shostakovich (op.34), and the fugues of Hindemith's `ludus tonalis' (one fugue for each pitch class, neither major nor minor). For the purpose of investigation we employ supervised and unsupervised machine learning techniques. In a supervised approach we investigated the ability of classifiers to recognize composers from profiles. As unsupervised methods we performed (1) a cluster analysis which resulted in one major and one minor cluster, and (2) a visualization technique called Isomap which reveals in its 2-dimensional representation some additional structure apart from the major--minor duality. In summary it is astonishing how much information on a music piece is contained in the 12-dimensional profiles that can be calculated in a straight-forward manner from any digitized music recording.

AES Convention: Paper Number:
Publication Date:
Session Subject:

Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!

This paper costs $33 for non-members and is free for AES members and E-Library subscribers.

Learn more about the AES E-Library

E-Library Location:

Start a discussion about this paper!

AES - Audio Engineering Society