Most systems for simulating sound propagation in a virtual environment for interactive applications use ray- or path-based models of sound. With these models, the "early" (low-order) specular reflection paths play a key role in defining the "sound" of the environment. However, the wave nature of sound, and the fact that smooth objects are approximated by triangle meshes, pose challenges for creating realistic approximations of the reflection results. Existing methods which produce accurate results are too slow to be used in most interactive applications with dynamic scenes. This paper presents a method for reflections modeling called spatially sampled near-reflective diffraction (SSNRD), based on an existing approximate diffraction model, Volumetric Diffraction and Transmission (VDaT). The SSNRD model addresses the challenges mentioned above, produces results accurate to within 1-2 dB on average compared to edge diffraction, and is fast enough to generate thousands of paths in a few milliseconds in large scenes. This method encompasses scene geometry processing, path trajectory generation, spatial sampling for diffraction modeling, and a small deep neural network (DNN) to produce the final response of each path. All steps of the method are GPU-accelerated, and NVIDIA RTX real-time ray tracing hardware is used for spatial computing tasks beyond just traditional ray tracing.

This paper presents a machine learning Deep Belief Network technique for interpolation and extrapolation of HRTF (Head Related Transfer Function) databases. In this technique, we decouple the stereo pair of HRTFs for each ear. Furthermore, we remove the inter-aural time differences (ITD) and distance attenuation from the recorded HRTF measurements such that the DBNs only interpolate and extrapolate the spectrum filtering of the audio for the two ears. Testing on the CIPIC and SCUT databases produces results of an average log spectral distortion less than 3 dB for all points around the head.