AI Briefing[GTC 2022] Part 1: Digital Avatar Technology Continues to Grow and Evolve
Key point
This summarizes the classification of digital avatars presented at NVIDIA GTC 2022, along with the ACE technology that implements them and its use cases.
Details
The digital avatar market is expected to grow to $527.76 billion by 2030, and is broadly classified into three forms: digital assistants, AI service agents, and virtual influencers.
NVIDIA introduced Omniverse ACE (Avatar Cloud Engine), a collection of cloud-based AI models and services, to simplify the complex avatar-building process. The key core technologies are as follows.
- Audio2Face: Generates real-time facial animation based on audio input, with support for emotion control and character retargeting.
- Text-to-Speech (TTS): Converts text into natural speech, enabling customized voice generation by adjusting pitch, speed, pronunciation, and more.
Applications that combine these technologies include Tokkio, a customer-service kiosk service, and Maxine, which supports gaze correction and automatic translation during video conferencing.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Stanford and NVIDIA Release 'Contrastive Language Model' CLM with 9x Faster Inference