At GTC 2022, NVIDIA revealed major updates to its suite of NVIDIA AI frameworks for building real-time speech AI applications, designing high-performing…
At GTC 2022, NVIDIA revealed major updates to its suite of NVIDIA AI frameworks for building real-time speech AI applications, designing high-performing recommenders at scale, applying AI to cybersecurity challenges, creating AI-powered medical devices, and more.
Showcased real-world, end-to-end AI frameworks highlighted the customers and partners leading the way in their industries and domains. When organizations put their AI frameworks into production, enterprise support with NVIDIA AI Enterprise ensures the success of these AI applications.
Watch the keynote from founder and CEO Jensen Huang to explore the latest AI technology advancements from NVIDIA and learn new ways to put AI into production.
NVIDIA Riva
NVIDIA announced new updates to Riva, an accelerated SDK for enabling speech AI frameworks. Build and deploy fully customizable real-time AI pipelines with world-class automatic speech recognition (ASR) and text-to-speech (TTS): in the cloud, at the edge, on-premises, or on embedded devices.
Highlights:
- World-class ASR in two new languages: Hindi and French.
- 5–30% out-of-the-box accuracy improvement for English, Spanish, Mandarin, Russian, and German.
- Easy voice emphasis, volume, and pause control at inference time with the SSML API.
- Compact and simple one TTS model with multiple synthetic voices allowing voice selection at inference time.
- Embedded Riva with seven ASR languages and two out-of-the-box female and male English TTS voices below 100 ms latency.
- Access to NVIDIA AI experts, training, and knowledge-based resources through NVIDIA Enterprise Support with the purchase of NVIDIA AI Enterprise software.
Get started with downloading Riva, try guided Riva labs on ready-to-run infrastructure in LaunchPad, or get support for large-scale Riva deployments with NVIDIA AI Enterprise software.
Add these GTC sessions to your calendar:
- How to Make Your Conversational Application Talk
- Speech-to-Text at Scale
- Speech AI Demystified
- AI Development Platform Helps on Conversational AI
- Building Conversational AI Applications DLI course (additional session)
NVIDIA Morpheus
At GTC, NVIDIA announced updates to Morpheus, a GPU-accelerated cybersecurity framework that enables developers to create optimized AI pipelines for filtering, processing, and classifying large volumes of real-time data.
New data visualizations included with the latest Morpheus release aid security analysts in pinpointing anomalies, with built-in explainability, enabling them to quickly determine a set of actionable next steps to remediate.
Additional new features:
- Digital fingerprinting workflow including fine-tunable explainability and thresholding to customize for your environment.
- A new visualization tool for digital fingerprinting provides massive data reduction for analyzed events so that security analysts can more quickly investigate and remediate.
- Visual graph-based explainer for sensitive information detection use cases enables security analysts to identify leaked sensitive data more easily.
- Multi-process pipeline support enables new workflows to be intelligently batched to reduce latency.
Learn more about the latest release of NVIDIA Morpheus. Get started with NVIDIA Morpheus on the nv-morpheus/Morpheus GitHub repo or NGC, or try it on NVIDIA LaunchPad.
Add these GTC sessions to your calendar:
- Learn About the Latest Developments with AI-Powered Cybersecurity
- Deriving Cyber Resilience from the Data Supply Chain
- Accelerating the Next Generation of Cybersecurity Research
NVIDIA cuOpt
NVIDIA announced the worldwide open availability of its cuOpt AI logistics software framework. cuOpt offers near real-time routing optimizations, empowering businesses to make use of larger data sets with faster processing.
Companies can now employ new capabilities such as dynamic rerouting, simulations, and subsecond solver response time for last-mile delivery, supply chain management, and warehouse picking.
Major updates:
- New containerized server API
- Availability on major public clouds such as GCP, AWS, Azure, and more
- Solving 700 variants of routing problems with top accuracy, speed, and scale to 10K locations per GPU
- Ability to connect with NVIDIA Isaac Sim to discover the speed of light in your next intralogistics design
- Leverage cuOpt’s world-record accuracy, based on benchmarks of Gehring and Homberger’s vehicle routing (CVRPTW) and Li&Lim’s pick up and deliveries (PDPTW) benchmark
For more information, download NVIDIA cuOpt on the /nvidia/cuopt-resources GitHub repo or try it on NVIDIA LaunchPad.
Add these GTC sessions to your calendar:
- Solving the Largest Optimization Problems in Seconds with Parallel Heuristics
- Optimizing Digital Twins to Reduce Intra-Factory Costs up to 20%
- How AT&T Supercharged their Data Science Efforts
NVIDIA Merlin
Today, NVIDIA announced updates to NVIDIA Merlin, an end-to-end recommender systems framework designed to accelerate data processing, training, inference, and deployment at scale.
With the latest release, data scientists and machine learning engineers can quickly build and deploy models on CPU and GPU, as well as scaling to terabyte (TB) size model training and inference.
Noted features:
- Easily build and compare common popular retrieval and ranking models across TensorFlow, XGBoost, and Implicit.
- Ability to build sequential and session-based recommendations by leveraging Hugging Face transformer-based architectures.
- Discovering model-parallelism for distributed embeddings that optimize TB model training for scalability and flexibility.
- Scaling inference to TB models with low latency and high throughput.
Ease your recommender experimentation frameworks and download it from the NVIDIA-Merlin GitHub repo today.
Add these GTC sessions to your calendar:
- Cross-Framework Model Evaluation and Accelerated Training with NVIDIA Merlin
- A Transformer-Powered Recommendation Engine for Personalized Online Advertising
NVIDIA Tokkio
At GTC, NVIDIA presented how NVIDIA Avatar Cloud Engine (ACE) is being used to put together incredibly complex avatar applications, including Tokkio, a reference application for building immersive, avatar-powered customer experiences.
Try out Tokkio today on NGC.
NVIDIA Maxine
At GTC, NVIDIA announced the early-access release of Maxine audio effects microservices, as well as two new audio SDK features. NVIDIA also shared the general availability of Eye Contact, Facial Expression Estimation, and other enhanced versions of existing SDKs.
The following NVIDIA Maxine microservices are in early access:
- Audio Super Resolution: Improves real-time audio quality by upsampling the audio input stream from 8 kHz to 16 kHz and the sampling rate from 16 kHz to 48 kHz.
- Acoustic Echo Cancellation: Cancels real-time acoustic device echo from input-audio stream, eliminating mismatched acoustic pairs and double-talk. With AI-based technology, more effective cancellation is achieved than with traditional digital signal processing.
- Background Noise Removal: Enables noise removal on users’ microphones as well as the audio feed of counterparts to make conversations easier to understand.
- Room Echo Removal: Removes audio of the voice that is heard by a microphone.
Get started with NVIDIA Maxine today.
Add this GTC session to your calendar:
MONAI 1.0
Project MONAI, the medical open network for AI, is continuing to expand its capabilities to accelerate medical AI training no matter where developers are starting in their medical AI framework.
The release of MONAI 1.0 brings exciting new updates:
- Model Zoo to jumpstart AI training frameworks
- Active Learning in MONAI Label for building better datasets
- Auto-3D Segmentation
- Federated Learning
For more about MONAI 1.0, see Open-Source Healthcare AI Innovation Continues to Expand with MONAI 1.0 or try it on NVIDIA LaunchPad.
Add these GTC sessions to your calendar:
- AI-Assisted Annotation for Continuous Learning with MONAI Label
- Take Medical AI from Research to Clinical Production with MONAI and Clara Holoscan
- Design, Train, and Evaluate Domain-Specialized Healthcare Imaging AI Models with MONAI
- Creating Inference Applications for the Medical AI Project Lifecycle using MONAI Deploy
NVIDIA Clara Holoscan
Announced at GTC, NVIDIA Clara Holoscan SDK 0.3 now provides a lightning-fast frame rate of 240 Hz for 4K video that enables you to combine data from more sensors and build AI applications that can provide surgical guidance. With faster data transfer enabled through high-speed, Ethernet-connected sensors, you have even more tools to build accelerated AI pipelines for medical devices.
Highlights:
- End-to-end latency of only 10 ms on a 4K 240 Hz stream
- Streaming data at 4K 60 Hz at under 50 ms on NVIDIA RTX A6000, teams can run 15 concurrent video streams and 30 concurrent models.
- Faster data transfer and scalable connectivity for high-bandwidth network sensors.
- Developer tools to build accelerated AI pipelines for versatile medical device applications.
Seeking a hands-on lab? Try Clara Holoscan on LaunchPad.
Add this GTC session to your calendar:
NVIDIA Metropolis
At GTC, NVIDIA announced that Siemens, the largest industrial automation company in the world, is adopting NVIDIA Metropolis and the IGX industrial edge AI platform. Metropolis on IGX will help Siemens connect entire fleets of robots and IoT devices to work together and proactively identify safety risks on factory floors and product defects on assembly lines with higher accuracy.
Additional benefits:
- Metropolis enables Siemens to integrate next-level perception with new and existing industrial inspection systems.
- With Metropolis and IGX, Siemens can connect a simulated digital twin factory to the physical twin, a huge step toward self-driving factories of the future.
Add these GTC sessions to your calendar:
- Tracking Objects Across Multiple Cameras Made Easy with Metropolis Microservices
- All You Need to Know About Implementing Parallel Pipelines with DeepStream
- AI Models Made Simple using NVIDIA TAO
NVIDIA Isaac
Today, NVIDIA introduced NVIDIA Isaac Sim on the cloud, providing three options to access photo-real, physically accurate robotics simulation using the newly released Omniverse Cloud, AWS RoboMaker, or self-managed instances. NVIDIA also announced NVIDIA Isaac Nova Orin as a modular and scalable compute and sensor platform for OEMs and ISVs working on autonomous mobile robots (AMRs).
Here’s how NVIDIA Isaac Sim and NVIDIA Isaac Nova Orin are helping to advance the robotics industry:
- Simulate robots anywhere and on any device.
- Scale simulations to meet the most compute-intensive simulation tasks like CI/CD and synthetic data generation.
- Accelerate AMR development with an interoperable sensor and compute platform.
Be sure to attend the two-hour, hands-on NVIDIA Isaac Sim on AWS Robomaker workshop.
Add these GTC sessions to your calendar:
- A Perspective on the Future of Robotics and Its Use Cases in Logistics and Smart Transportation
- Leveraging Simulation Tools to Develop AI-Based Robots
- OV: How to Build a Digital Twin: Bringing in Robotics
- Re-imagining Robot Autonomy with Neural Environment Representations
NVIDIA DRIVE Thor
Today, NVIDIA introduced NVIDIA DRIVE Thor, its next-generation centralized computer to ensure safe and secure autonomous vehicles.
NVIDIA DRIVE Thor is a superchip that achieves 2,000 teraflops of performance and can unify intelligent functions into a single architecture for greater efficiency and lower overall system cost. Smart functions include automated and assisted driving, parking, driver and occupant monitoring, digital instrument cluster, in-vehicle infotainment (IVI), and rear-seat entertainment.
New features:
- Multi-domain computing support
- FP8 precision
- Inference transformer engine, improving DNN performance by 9x
- NVLink-C2C chip interconnect technology
For more information about NVIDIA DRIVE Thor capabilities, see NVIDIA DRIVE Thor Strikes AI Performance Balance, Uniting AV and Cockpit on a Single Computer.
Add these GTC sessions to your calendar:
- Developing Software-Defined Vehicles for the New Era of Transportation
- Elevating the Passenger Experience with Intelligent In-Vehicle Infotainment
- Turbocharging DNN Development and Testing for Autonomous Vehicles with DGX SuperPOD
- Accelerating AV Development and Validation with Synthetic Data Generation
NVIDIA BioNeMo
Just as AI is learning to understand human languages with transformer models, it’s also learning the languages of biology and chemistry. At GTC, NVIDIA introduced BioNeMo, a new framework and service for training large-scale transformer models using bigger datasets. This results in better-performing neural networks.
Larger models can store more predictive information on amino acid sequences and properties of different proteins. You can connect these insights to biological properties, functions, and even human health conditions.
Highlights:
- Pretrained large language models (LLMs) for chemistry and biology
- Optimized inference at supercomputing scale, enabling you to deploy LLMs with billions or trillions of parameters
- Turnkey cloud service for AI drug discovery pipelines
Try MegaMolBART, a generative chemistry model in the BioNeMo framework, with a guided lab on LaunchPad.
Add this GTC session to your calendar:
NVIDIA AI Enterprise
NVIDIA AI Enterprise is a powerful cloud-native software suite that streamlines the entire AI framework and unlocks the full potential of the NVIDIA AI platform.
As the operating system of the NVIDIA AI platform, NVIDIA AI Enterprise provides production-ready support for applications built with the extensive NVIDIA library of frameworks.
Whether it’s creating more engaging chatbots and AI virtual assistants with Riva, building smarter recommendations to help consumers make better purchasing decisions with NVIDIA Merlin, or developing AI-powered medical imaging and genomics with NVIDIA Clara, and more, NVIDIA AI Enterprise supports NVIDIA domain-specific frameworks that developers can use to design new business solutions.
Add these GTC sessions to your calendar: