CA/AXR - Acoustical Extended Reality and Computer Audition
Prof. Dr. Michael Oehler
The basic idea is focused on two partial connected pillars: Acoustical Extended Reality (AXR) and Computer Audition (CA). The two areas can be assigned to the field of Music Informatics or Digital Musicology. AXR uses virtual-, augmented- or mixed-reality-technologies in connection with music-related research questions, CA uses methods from the field of artificial intelligence (AI) to obtain semantic information from audio files, e.g. determination of the genre or recognition of emotions. CA and AXR deal with important social challenges of the future, which, methodically anchored in music technology and systematic musicology respectively, are to be addressed from an interdisciplinary perspective.
Two exemplary subject areas, which are in the focus of our interest, are:
a) Technology and future significance of immersive acoustic virtual environments
This applies, for example, to simultaneous but spatially separated rehearsals/concerts and the associated effects on artistic formats and reception, as well as to the therapeutic use of acoustic virtual environments (e.g. for the creation of participation opportunities for people with reduced mobility or for the rehabilitation of the hearing impaired).
b) Transformation of music production and reception caused by AI
Although music and media technology has always influenced the way we make and listen to music, current developments in the field of AI suggest far more fundamental changes for the future. These include, for example, the autonomous composition and production of music via AI and the increasing importance and omnipresence of digital music services, which can influence music production and reception by combining the analysis of user data and the semantic analysis of audio files.
Funded by the Volkswagen Foundation, 2020 -2026
Principal investigator: Prof. Dr. Michael Oehler, Osnabrück University
Project team: Dr. Maurício do Vale Madeira da Costa, Max Westkemper