On the Reduction of Large-Scale Room Acoustic Models

Efficient sound density simulation for room acoustic models is a challenging problem, due to the need for the solution of large-scale systems of equations that require unreasonably long computational times. However, in many cases, the measurement of sound density is not required to be computed at every point of the entire room but only at certain spots. This makes the room acoustic problem amenable to Model Order Reduction (MOR) techniques. Moment-Matching (MM) techniques are well established and can be directly applied in the resulting sound diffusion equation. In this paper, we propose a computationally efficient MM algorithm based on extended Krylov subspace method, that can generate very compact models in order to efficiently simulate them across many timesteps. Experimental results demonstrate a speedup up to 1016x with relative error less than 0.5%.