JUNE 8 & 9, 2020 TRACKS

Digital Humans | Artificial Intelligence | Machine Learning | GANs
Panelists Presentation

AI based Conversational Digital Characters

Simon Yuen – NVIDIA

In this talk, I will first give a quick overview of Jarvis, NVIDIA’s multimodal end to end conversational AI framework. I will use Misty, a conversational AI weather chatbot to demonstrate how this framework plus Nvidia’s Omniverse can help create an AI-driven 3D digital avatar. I will then dive deeper into Audio2Face, the audio-driven AI-based facial animation technology that powers Misty’s automatic facial animation based on her synthesized voice in real-time. I will also demonstrate this technology on a more realistic face to show how this can work in both stylized and realistic facial animation, what we can do with this technology, and how it can work with different voices and languages to automatically generate detail believable motion.

Personal Profile
Simon Yuen
Director of graphics AI – NVIDIA
Linkedin

Simon Yuen is Director of Graphics and AI at NVIDIA where he leads the Digital Human efforts with the goal of developing new character technology and deep learning-based solutions that allow new and more efficient ways of creating high-quality digital characters. Prior to NVIDIA, Simon spent more than 20 years in the visual effects industry, straddling both the art and technology sides of the problem at many studios including Method Studios, Digital Domain, Sony Pictures Imageworks, Dreamworks, Blizzard Entertainment and among others building teams and technologies that push the envelope of photorealistic digital character creation.

Previous

Subscribe to the RTC newsletter