Using AI-enabled speech control to increase immersion for XR design review

In using immersive systems such as VR and XR for design review, a key attribute of the system is a seamless interaction with at-scale - realistic digital models. Autodesk VRED is a well-accepted manufacturing design review application, offering close to truth photorealism and a highly-immersive XR interface. In using AI-enabled speech control with VRED, the level of immersion is increased, allowing a user direct interaction with the digital model without the need of scene-occluding GUIs. It also allowing the user to naively interact with VRED, enabling more users to perform unassisted design reviews in XR. Project Mellon is NVIDIA's internal speech enablement project that uses the state-of-the-art Riva ASR with a prototype dialog manager and 0-shot learning NLP to achieve a developer-friendly integration of AI-enabled speech. In this session, we will show Mellon/VRED and discuss how Mellon is used to easily update command lists without the need of extensive NLP training.

Key Learnings