Andre Holzapfel

Music Research

Bogazici University







Private Life


The Lise-Meitner project
A deeper understanding of common elements in musical rhythm

In May 2016, this two year individual postdoc project started, funded by the FWF Austria. It had to be suspended after 6 months, due to my new position at KTH in Sweden. Below the initial abstract, which describes the project plan.

Project abstract

When listening to an unfamiliar style of music, we attempt to tap the beat and to synchronise with the rhythm, a process that enables us to interpret the structure of what we hear. This process is made possible by music universals, properties of music encountered in cultures throughout the whole world. In this project, we will discover universals in musical rhythm and their culturally dependent interpretation by applying a novel multidisciplinary methodology that combines the perspectives of music information retrieval (MIR) and ethnomusicology. Our insights into universals of musical rhythm will be shaped into universal models for the analysis of temporal structure in the musics of the world. Such models represent an important contribution to temper the existing bias towards Western music in MIR research, and can contribute to systems that can cope with a larger cultural diversity of music.

In this very moment, the epoch-making development of deep learning gives us the tool to explore the borders and potentials of machine learning in application to music as a cultural expression. We will pursue discovering universals by answering important research questions from ethnomusicology with the help of innovative universal models that combine deep learning and Bayesian modelling. Deep learning enables the discovery of low-level universal signal properties, and Bayesian models enable for inclusion of expert knowledge and culturally dependent high-level interpretation. 

Our developed models will offer perspectives for a fair and balanced music recommendation and distribution in digital platforms and offer radically novel scientific perspectives on music analysis within engineering and humanities. Our project will promote a deeper understanding of music that suits the needs of a new digital age and indicates ways to connect musicians and listeners across cultural borders.


1.: Holzapfel, A. & Benetos, E. (2016), The Sousta corpus: Beat-informed automatic transcription of traditional dance tunes, in 'Proceedings of ISMIR - International Conference on Music Information Retrieval', pp. 531-537.

2.: Holzapfel, A. & Grill, T. (2016), Bayesian meter tracking on learned signal representations, in 'Proceedings of ISMIR - International Conference on Music Information Retrieval', pp. 262-268.