Introducing HP VR Spatial Audio
With the official launch of the HP Omnicept SDK, we want to highlight an important new feature. HP VR Spatial Audio enables an immersive sound environment in your VR applications where users perceive sound sources to originate from their relative position in the virtual environment. Perceptually, people rely on subtle differences in the way sound reaches their left ear vs. their right ear to localize where a sound is coming from. These subtle differences between ears are known in the audio community as Head-Related Transfer Functions (HRTFs). Creating realistic virtual sound environments is challenging because each individual has different HRTFs for different sound orientations because of differences in ear lobe shape, head shape, and ear position. HP VR Spatial Audio uses a unique Machine Learning approach to predict in real time the optimal HRTF for each sound source in the scene. Our ML approach provides a more realistic and natural sound localization that creates a better audio experience for a diverse and varied population of users.
For more details on the journey of creating HP VR Spatial Audio in HP Labs, see: https://garage.hp.com/us/en/hp-labs/hp-labs-spatial-audio-research-adds-powerful-presence-to-vr-and-other-environments.html
And for deeper technical review of our approach, see: https://blogs.mathworks.com/deep-learning/2020/05/05/optimization-of-hrtf-models/