TU Berlin

Neural Information ProcessingMachine Learning and Neural Networks for the Perceptually Relevant Analysis of Music

Neuronale Informationsverarbeitung

Page Content

to Navigation

Machine Learning and Neural Networks for the Perceptually Relevant Analysis of Music


Music contains structural information as well as semantic connotations which are easy to perceive by human listeners, but which are difficult to extract automatically from an acoustic event (and even from the score of a given piece of music). Here we explore new techniques from the machine learning and the mathematical music theory fields with the goal to create semantically meaningful representations from acoustic events and to automatically extract perceptually relevant patterns from music and sound.

Acknowledgement: Research was funded by the EU and by the Technische Universität Berlin.

Selected Publications:

Purwins, H., Blankertz, B. and Obermayer, K. (2008). Toroidal Models in Tonal Theory. Tonal Theory for the Digital Age - Computing in Musicology. Stanford University, 73 – 98.,

Adiloglu, K. and Obermayer, K. (2007). Topological Features of the Two-Voice Inventions. Communications in Computer and Information Science. Springer Berlin Heidelberg, 67 – 73.,10.1007/978-3-642-04579-0_7

Adiloglu, K., Noll, T. and Obermayer, K. (2006). A Paradigmatic Approach to Extract the Melodic Structure of a Musical Piece. Journal New Music Research, 35, 221 – 236.

Purwins, H., Normann, I. and Obermayer, K. (2005). Unendlichkeit - Konstruktion musikalischer Paradoxien. Mikrotöne und mehr: Auf György Ligetis Hamburger Pfaden. Bockel-Verlag, 39 – 80.,

Purwins, H., Graepel, T. and Obermayer, K. (2004). Correspondence Analysis of Pitch Class, Key, and Composer. Perspectives of Mathematical and Computational Music Theory. Epos-Verlag, 432 – 454.,

Purwins, H., Blankertz, B. and Obermayer, K. (2000). Computing Auditory Perception. Organised Sound, 5, 159 – 171.

To top


Quick Access

Schnellnavigation zur Seite über Nummerneingabe