direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

Martin Herzog






born in Berlin, Germany, August 20th 
Study of Computer Science at Humboldt University Berlin (Diploma 2011)
Freelance web developer
Student worker at ]init[ AG for Digital Communication
Diploma thesis: „Harmony Analysis of MIDI Data as a Basis for the Extraction of Harmonic High-Level-Features“ 
since 2011
Consultant at ]init[ AG for Digital Communication
since 2016
Research associate at TU Berlin
Current project: ABC_DJ (Artist-to-Business-to-Business-to-Consumer Audio Branding System)
PhD project: Predicting Musical Meaning from High-Level Music Features

PhD Project

Predicting Musical Meaning from High-Level Music Features

What is the link between musical content on one hand and perceived musical meaning on the other?

In my PhD project I investigate the question which features – derived from music theory – play an important role in predicting perceived musical meaning. Using data from a large-scale lsitening experiment, I aim to develop a Multilevel Linear Regression Model for the prediction of perceived semantics in popular music.

Supervisors: Prof. Dr. Stefan Weinzierl (TU Berlin), Dr. Hauke Egermann (University of York, UK)

Research Interests

  • Music perception and processing
  • Music and emotion
  • Music information retrieval
  • Audio branding


Herzog, M., Lepa, S., Steffens, J., Schönrock, A. & Egermann, H. (2017): Predicting musical meaning in audio branding scenarios. Proceedings of the 25th Anniversary Conference of the European Society for Cognitive Science of Music, Ghent, Belgium, 2017

Steffens, J., Lepa, S., Egermann, H., Schönrock, A. & Herzog, M. (2017): Entwicklung eines Systems zur automatischen Musikempfehlung im Kontext des Audio Brandings. In: Fortschritte der Akustik: Tagungsband d. 43. DAGA. Deutsche Gesellschaft für Akustik, 2017

Herzog, M., Lepa, S. & Egermann, H. (2016): Towards automatic music recommendation for audio branding scenarios. Proceedings of the ISMIR 2016 conference, New York, USA, 2016

Zusatzinformationen / Extras


Schnellnavigation zur Seite über Nummerneingabe

Diese Seite verwendet Matomo für anonymisierte Webanalysen. Mehr Informationen und Opt-Out-Möglichkeiten unter Datenschutz.