NVIDIA reveals Jarvis Conversational AI tech, demos Misty AI weather chatbot
Along with the DGX A100 AI GPU, NVIDIA revealed the Jarvis Conversational AI tech.
During the GTC 2020 virtual keynote, NVIDIA CEO and founder Jensen Huang interacted with Misty.
Misty is based on the NVIDIA Jarvis. It's a conversational AI weather chatbot with an I-driven 3D digital avatar that can understand a question and answer a question with facial expressions. It has a natural language understanding and more.
NVIDIA explained that the 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.
Jarvis also uses the Audio2Face, an audio-driven AI-based technology, to automatically create the real-time facial animation from the synthesized speech of Jarvis.
These will be rendered in real-time using NVIDIA Omniverse, a multi-GPU, and a real-time simulation and collaboration platform for 3D production pipelines.
NVIDIA also noted that Jarvis has deep learning and trainable as well.
Source: NVIDIA
 |
| Misty |
During the GTC 2020 virtual keynote, NVIDIA CEO and founder Jensen Huang interacted with Misty.
Misty is based on the NVIDIA Jarvis. It's a conversational AI weather chatbot with an I-driven 3D digital avatar that can understand a question and answer a question with facial expressions. It has a natural language understanding and more.
NVIDIA explained that the 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.
Jarvis also uses the Audio2Face, an audio-driven AI-based technology, to automatically create the real-time facial animation from the synthesized speech of Jarvis.
These will be rendered in real-time using NVIDIA Omniverse, a multi-GPU, and a real-time simulation and collaboration platform for 3D production pipelines.
NVIDIA also noted that Jarvis has deep learning and trainable as well.
Source: NVIDIA
Post a Comment