Room Impulse Response Reconstruction Based on Spatio-Temporal-Spectral Features Learned from a Spherical Microphone Array Measurement

Abstract

Large-scale Room Impulse Response (RIR) measurements are required to accurately determine a room's acoustic response to different source-listener configurations. RIR reconstruction methods are often used to reduce these measurement costs. Prior knowledge of room acoustic parameters can ensure reliable and robust RIR reconstruction. This paper proposes a method to reconstruct RIRs based on reflection source locations and time-frequency-direction-dependent reflection magnitude response estimated from a single spherical microphone array measurement. These input parameters are learned by applying the eigenbeam spatial correlation method and von Mises-Fisher (vMF)-based directivity modeling. According to the performance evaluation, the composition of the learned features in the RIR reconstruction formulation successfully preserves the objective characteristics of the real room.