Opens in a new tab

AES E-Library

← Back to search

Conference Paper Open Access

Realistic Auditory Artificial Intelligence: Spatial Sound Modelling to provide NPCs with Sound Perception

Authors: Cowan, Brent; Kapralos, Bill; Collins, KC

AES Conference: 2020 AES International Conference on Audio for Virtual and Augmented Reality (August 2020) · Paper 2-6 · August 2020

Abstract

Despite advancements in AI for games in recent years, non-player characters (NPCs) still do not perceive the world in a realistic manner. NPC’s sense of hearing has been limited or ignored. Building on our previous work that saw the development of GrAF, a graph-based spatial sound framework capable of modelling the propagation of sound through complex three dimensional virtual environments in real-time, here we apply this method to NPCs, providing them with the ability to “perceive” sounds in a more realistic manner, ultimately leading to more realistic NPC behavior.

Details

Published in
AES Conference: 2020 AES International Conference on Audio for Virtual and Augmented Reality (August 2020)
Paper number
2-6
Publication date
August 6, 2020
Affiliation
Ontario Tech University; University of Waterloo (See document for exact affiliation information.)
Type
Conference Paper