Predicting Musical Meaning in Audio Branding Scenarios

Martin Herzog, Steffen Lepa, Jochen Steffens, Andreas Schoenrock, Hauke Wolfgang Egermann

Research output: Chapter in Book/Report/Conference proceedingConference contribution


This paper describes the concept of applying automatic music recommendation to the audio branding domain. We describe our approach of developing a prediction model for the perceived expressive content of music which is based on a large-scale listening experiment. We present an orthogonal 4-factor model for measuring musical expression as outcome variable, whereas audio- and music features as well as lyric-based features are introduced as prediction variables in the model. Furthermore, we describe Random Forest Regression as a concept for feature selection required to develop a Multi-Level Regression Model, which is taking individual listener parameters into account. Finally, we present first results from a preliminary stepwise regression model for perceived musical expression.
Original languageEnglish
Title of host publicationProceedings of the 25th Anniversary Conference of the European Society for Cognitive Science of Music, Ghent, Belgium, 31 July – 4 August 2017
EditorsE. Van Dyck
Number of pages5
Publication statusPublished - 31 Jul 2017
EventEuropean Society for Cognitive Sciences Of Music Conference - Ghent, Belgium
Duration: 31 Jul 20174 Aug 2017


ConferenceEuropean Society for Cognitive Sciences Of Music Conference
Abbreviated titleESCOM 2017


  • Music Branding
  • Audio Branding
  • Musical Semantics
  • Music Information Retrieval

Cite this