GTC 2020: Intelligent End-to-End AI Chatbot with Audio-Driven Facial Animation
After clicking “Watch Now” you will be prompted to login or join.
You will be prompted to login or join.
Click “Watch Now” to login or join the NVIDIA Developer Program.
Intelligent End-to-End AI Chatbot with Audio-Driven Facial Animation
Tech Demo Team, NVIDIA
During the GTC 2020 virtual keynote, NVIDIA CEO and founder Jensen Huang interacted with Misty, a conversational AI weather chatbot, to demonstrate an end-to-end pipeline to create an AI driven 3D digital avatar. The NVIDIA Jarvis multimodal application framework includes pre-trained conversational AI models, and optimized end-to-end services for speech, vision, and natural language understanding (NLU) tasks. It also includes Audio2Face, an audio driven AI-based technology, to automatically create the real-time facial animation from the synthesized speech of Jarvis. All of this is rendered in real-time with NVIDIA Omniverse, a powerful, multi-GPU, real-time simulation and collaboration platform for 3D production pipelines.
Learn more about NVIDIA Jarvis
Learn more about NVIDIA Omniverse
Watch the entire GTC 2020 keynote