Contribution
Binaural room impulse responses interpolation using physics-informed neural networks in three dimensions
* Presenting author
Abstract:
Binaural room impulse responses (BRIRs) are a combination of room impulse responses (RIRs) and head-related impulse responses (HRIRs) that contain both room information and spatial perception information, where in-situ measurements are difficult. BRIRs interpolation is solved using traditional DSP methods. We propose to use deep learning to learn the implicit representation of BRIRs from a sparse measurements and add physics constraints to improve the performance. Our results show that the proposed method can overcome the problems in traditional methods.