NVIDIA announced the re-architecture of Maxine for cloud-native microservices.
NVIDIA announced the re-architecture of Maxine for cloud-native microservices along with its new features: Speaker Focus, Face Expression Estimation, and Eye Contact. The service enables clear communications to enhance virtual interactions.
Maxine’s cloud-native microservices allow developers to build real-time AI applications. They can be independently managed and deployed seamlessly in the cloud.
The Audio Effects microservice is available in early access and provides Background Noise Removal, Room Echo Removal, Audio Super Resolution, and Acoustic Echo Cancellation.
Maxine's GPU-accelerated SDKs offer:
- Speaker Focus – a new feature that separates the audio tracks of foreground and background speakers.
- Audio Super Resolution has been updated with enhanced quality.
- Virtual Background, which segments a person’s profile and applies AI-powered background removal, replacement, or blur, has been updated with enhanced temporal stability.
- Eye Contact simulates eye contact by estimating and aligning gaze with the camera.
- Face Expression Estimation – tracks the face and infers what expression is presented by the subject.
One of the most interesting new features is Eye Contact. The AI keeps your gaze on the camera, which can be useful when you're reading from a teleprompter or bringing up the next slide of the presentation.
NVIDIA Maxine is a suite of GPU-accelerated AI software development kits (SDKs) and cloud-native microservices for deploying optimized and accelerated AI features that enhance audio, video, and augmented reality (AR) effects in real-time.