Data-driven Room Acoustic Modelling for AR (DRAMA)

Research Student: Amal Emthyas
Supervisor: Dr Enzo De Sena
Co-Supervisor: TBC
Industrial Partner & Funding: Facebook Reality Labs

Start date: 2022
End date: 2026

Project Outline

In augmented reality (AR) applications, virtual sound sources need to be rendered in a manner that is consistent with the acoustics of the room where the user is physically located. This is necessary for the virtual sources to be perceived as believable and correctly externalised, and for the overall auditory experience comprising real and virtual sound sources to feel seamless and natural. Data-driven room acoustic models are particularly well suited in this context as they can leverage measurements of the actual room. DRAMA will define new data-driven models that are specifically tailored to applications in AR, enabling end-users to benefit from DRAMAtic improvements in the quality of the auditory experience.