Sony Pixel Power calrec Sony

Speak Like a Native: NVIDIA Parlays Win in Voice Challenge

14/02/2024

Thanks to their work driving AI forward, Akshit Arora and Rafael Valle could someday speak to their spouses' families in their native languages.

Arora and Valle - along with colleagues Sungwon Kim and Rohan Badlani - won the LIMMITS '24 challenge which asks contestants to recreate in real time a speaker's voice in English or any of six languages spoken in India with the appropriate accent. Their novel AI model only required a three-second speech sample.

The NVIDIA team advanced the state of the art in an emerging field of personalized voice interfaces for more than a billion native speakers of Bengali, Chhattisgarhi, Hindi, Kannada, Marathi and Telugu.

Making Voice Interfaces Realistic The technology for personalized text-to-speech translation is a work in progress. Existing services sometimes fail to accurately reflect the accents of the target language or nuances of the speaker's voice.

The challenge judged entries by listening for the naturalness of models' resulting speech and its similarity to the original speaker's voice.

The latest improvements promise personalized, realistic conversations and experiences that break language barriers. Broadcasters, telcos, universities, as well as e-commerce and online gaming services are eager to deploy such technology to create multilingual movies, lectures and virtual agents.

We demonstrated we can do this at a scale not previously seen, said Arora, who has two uses close to his heart.

Breaking Down Linguistic Barriers A senior data scientist who supports one of NVIDIA's biggest customers, Arora speaks Punjabi, while his wife and her family are native Tamil speakers.

It's a gulf he's long wanted to bridge for himself and others. I had classmates who knew their native languages much better than the Hindi and English used in school, so they struggled to understand class material, he said.

The gulf crosses continents for Valle, a native of Brazil whose wife and family speak Gujarati, a language popular in west India.

It's a problem I face every day, said Valle, an AI researcher with degrees in computer music and machine listening and improvisation. We've tried many products to help us have clearer conversations.

Badlani, an AI researcher, said living in seven different Indian states, each with its own popular language, inspired him to work in the field.

A Race to the Finish Line The initiative started nearly two years ago when Arora and Badlani formed the four-person team to work on the very different version of the challenge that would be held in 2023.

Their efforts generated a working code base for the so-called Indic languages. But getting to the win announced in January required a full-on sprint because the 2024 challenge didn't get on the team's radar until 15 days before the deadline.

Luckily, Kim, a deep learning researcher in NVIDIA's Seoul office, had been working for some time on an AI model well suited to the challenge.

A specialist in text-to-speech voice synthesis, Kim was designing a so-called P-Flow model prior to starting his second internship at NVIDIA in 2023. P-Flow models borrow the technique large language models employ of using short voice samples as prompts so they can respond to new inputs without retraining.

I created the model for English, but we were able to generalize it for any language, he said.

We were talking and texting about this model even before he started at NVIDIA, said Valle, who mentored Kim in two internships before he joined full time in January.

Giving Others a Voice P-Flow will soon be part of NVIDIA Riva, a framework for building multilingual speech and translation AI software, included in the NVIDIA AI Enterprise software platform.

The new capability will let users deploy the technology inside their data centers, on personal systems or in public or private cloud services. Today, voice translation services typically run on public cloud services.

I hope our customers are inspired to try this technology, Arora said. I enjoy being able to showcase in challenges like this one the work we do every day.

The contest is part of an initiative to develop open-source datasets and AI models for nine languages most widely spoken in India.

Hear Arora and Badlani share their experiences in a session at GTC next month.

And listen to the results of the team's model below, starting with a three-second sample of a native Kannada speaker:

https://blogs.nvidia.com/wp-content/uploads/2024/02/pr_kannada_f_indictts_prompt_3s-1.mp3

Here's a similar-sounding synthesized voice reading the first sentence of this blog in Hindi:

https://blogs.nvidia.com/wp-content/uploads/2024/02/pr_kannada_f_indictts_speaking_hindi_3-2.mp3

And then in English:

https://blogs.nvidia.com/wp-content/uploads/2024/02/pr_kannada_f_indictts_speaking_english-1.mp3 See notice regarding software product information.
LINK: https://blogs.nvidia.com/blog/generative-voice-challenge/...
See more stories from nvidia

More from Nvidia

18/09/2025

GeForce NOW Unleashes Dying Light: The Beast' in the Cloud

GeForce NOW is packing a monstrous punch this week. Dying Light: The Beast, the latest adrenaline fueled chapter in Techland's parkour meets survival horror...

17/09/2025

Meet the Streamlabs Streaming Assistant, Accelerated by NVIDIA RTX

Today's creators are equal parts entertainer, producer and gamer, juggling game commentary, scene changes, replay clips, chat moderation and technical troub...

16/09/2025

The AI Makers: NVIDIA Partners in UK Advance Physical and Agentic AI, Robotics, Life Sciences and More

The U.K. is driving investments in sovereign AI, using the technology to advance...

13/09/2025

Reaching Across the Isles: UK-LLM Brings AI to UK Languages With NVIDIA Nemotron

Celtic languages - including Cornish, Irish, Scottish Gaelic and Welsh - are the U.K.'s oldest living languages. To empower their speakers, the UK-LLM sover...

10/09/2025

Paint It Blackwell: GeForce RTX 5080 SuperPOD Rollout Begins

GeForce NOW Blackwell RTX 5080-class SuperPODs are now rolling out, unlocking a new level of ultra high-performance, cinematic cloud gaming. GeForce NOW Ultima...

09/09/2025

NVIDIA Rubin CPX Accelerates Inference Performance and Efficiency for 1M+ Token Context Workloads

Inference has emerged as the new frontier of complexity in AI. Modern models are...

09/09/2025

NVIDIA Blackwell Ultra Sets New Inference Records in MLPerf Debut

As large language models (LLMs) grow larger, they get smarter, with open models from leading developers now featuring hundreds of billions of parameters. At the...

09/09/2025

NVIDIA Partners With AI Infrastructure Ecosystem to Unveil Reference Design for Giga-Scale AI Factories

At this week's AI Infrastructure Summit in Silicon Valley, NVIDIA's VP o...

09/09/2025

NVIDIA Blackwell Ultra Sets the Bar in New MLPerf Inference Benchmark

Inference performance is critical, as it directly influences the economics of an AI factory. The higher the throughput of AI factory infrastructure, the more to...

09/09/2025

Safety First, Always,' NVIDIA VP of Automotive Says, Unveiling the Future of AI-Defined Vehicles at IAA Mobility

At this week's IAA Mobility conference in Munich, NVIDIA Vice President of A...

09/09/2025

Get Started Using Generative AI for Content Creation With ComfyUI and NVIDIA RTX AI PCs

ComfyUI - an open-source, node-based graphical interface for running and buildin...

04/09/2025

NVIDIA Pledges AI Education Funding for K-12 Programs

NVIDIA today announced new AI education support for K-12 programs at a White House event to celebrate public-private partnerships that advance artificial intell...

04/09/2025

AI On: 6 Ways AI Agents Are Raising Team Performance - and How to Measure It

Editor's note: This post is part of the AI On blog series, which explores the latest techniques and real-world applications of agentic AI, chatbots and copi...

04/09/2025

Cloud Gaming to Reach New Heights: GeForce NOW's Blackwell RTX Upgrade Begins Next Week

NVIDIA Blackwell RTX is coming to the cloud on Wednesday, Sept. 10 - an upgrade ...

03/09/2025

Scene It to Believe It: Populate 3D Worlds Quickly With NVIDIA AI Blueprints

3D artists are constantly prototyping. In traditional workflows, modelers must build placeholder, low-fidelity assets to populate 3D scenes, tinkering and adju...

02/09/2025

It's the Humidity: How International Researchers in Poland, Deep Learning and NVIDIA GPUs Could Change the Forecast

For more than a century, meteorologists have chased storms with chalkboards, equ...

28/08/2025

Drop Into the Battle: Gears of War: Reloaded Unleashed' Launches on GeForce NOW

Brace yourself, COGs - the Locusts aren't the only thing rising up. The Coal...

28/08/2025

Game On: How Modders Reimagine Classic Games With NVIDIA RTX Remix and Generative AI

Last week at Gamescom, NVIDIA announced the winners of the NVIDIA and ModDB RTX ...

27/08/2025

How Do You Teach an AI Model to Reason? With Humans

AI models are advancing at a rapid rate and scale. But what might they lack that (most) humans don't? Common sense: an understanding, developed through rea...

25/08/2025

NVIDIA Jetson Thor Unlocks Real-Time Reasoning for General Robotics and Physical AI

Robots around the world are about to get a lot smarter as physical AI developers...

25/08/2025

Take It for a Spin: NVIDIA Rolls Out DRIVE AGX Thor Developer Kit to World's Automotive Developers

As autonomous vehicle systems rapidly grow in complexity, equipped with reasonin...

22/08/2025

Inside NVIDIA Blackwell Ultra: The Chip Powering the AI Factory Era

As the latest member of the NVIDIA Blackwell architecture family, the NVIDIA Blackwell Ultra GPU builds on core innovations to accelerate training and AI reason...

22/08/2025

Hot Topics at Hot Chips: Inference, Networking, AI Innovation at Every Scale - All Built on NVIDIA

AI reasoning, inference and networking will be top of mind for attendees of next...

21/08/2025

RIKEN, Japan's Leading Science Institute, Taps Fujitsu and NVIDIA for Next Flagship Supercomputer

Japan is once again building a landmark high-performance computing system - not ...

21/08/2025

Think SMART: How to Optimize AI Factory Inference Performance

From AI assistants doing deep research to autonomous vehicles making split-second navigation decisions, AI adoption is exploding across industries. Behind ever...

21/08/2025

Gearing Up for the Gigawatt Data Center Age

Across the globe, AI factories are rising - massive new data centers built not to serve up web pages or email, but to train and deploy intelligence itself. Inte...

21/08/2025

GeForce NOW Brings RTX 5080 Power to the Ultimate Membership

Get a glimpse into the future of gaming. The NVIDIA Blackwell RTX architecture is coming to GeForce NOW in September, marking the service's biggest upgrade...

20/08/2025

Into the Omniverse: How OpenUSD and Digital Twins Are Powering Industrial and Physical AI

Editor's note: This blog is a part of Into the Omniverse, a series focused o...

18/08/2025

At Gamescom 2025, NVIDIA DLSS 4 and Ray Tracing Come to This Year's Biggest Titles

With over 175 games now supporting NVIDIA DLSS 4 - a suite of advanced, AI-power...

18/08/2025

New Lightweight AI Model for Project G-Assist Brings Support for 6GB NVIDIA GeForce RTX and RTX PRO GPUs

At Gamescom, NVIDIA is releasing its first major update to Project G Assist - an...

15/08/2025

Now We're Talking: NVIDIA Releases Open Dataset, Models for Multilingual Speech AI

Of around 7,000 languages in the world, a tiny fraction are supported by AI lang...

14/08/2025

NVIDIA, National Science Foundation Support Ai2 Development of Open AI Models to Drive U.S. Scientific Leadership

NVIDIA is partnering with the U.S. National Science Foundation (NSF) to create a...

14/08/2025

Warhammer 40,000: Dawn of War - Definitive Edition' Storms GeForce NOW at Launch

Warhammer 40,000: Dawn of War - Definitive Edition is marching onto GeForce NOW,...

13/08/2025

FLUX.1 Kontext NVIDIA NIM Microservice Now Available for Download

Black Forest Labs' FLUX.1 Kontext [dev] image editing model is now available as an NVIDIA NIM microservice. FLUX.1 models allow users to edit existing imag...

11/08/2025

Amazon Devices & Services Achieves Major Step Toward Zero-Touch Manufacturing With NVIDIA AI and Digital Twins

Using NVIDIA digital twin technologies, Amazon Devices & Services is powering bi...

11/08/2025

Mini Footprint, Mighty AI: NVIDIA Blackwell Architecture Powers AI Acceleration in Compact Workstations

Packing the power of the NVIDIA Blackwell architecture in compact, energy-effici...

11/08/2025

Making Safer Spaces: NVIDIA and Partners Bring Physical AI to Cities and Industrial Infrastructure

Physical AI is becoming the foundation of smart cities, facilities and industria...

07/08/2025

The Saga Continues: Stream 2K's Mafia: The Old Country' at Launch on GeForce NOW

This GFN Thursday brings an offer members can't refuse - 2K's highly ant...

05/08/2025

OpenAI and NVIDIA Propel AI Innovation With New Open Models Optimized for the World's Largest AI Inference Infrastructure

Two new open-weight AI reasoning models from OpenAI released today bring cutting...

05/08/2025

OpenAI's New Open Models Accelerated Locally on NVIDIA GeForce RTX and RTX PRO GPUs

In collaboration with OpenAI, NVIDIA has optimized the company's new open-so...

05/08/2025

Delivering 1.5M TPS Inference on NVIDIA GB200 NVL72, NVIDIA Accelerates OpenAI gpt-oss Models From Cloud to Edge

NVIDIA and OpenAI began pushing the boundaries of AI with the launch of NVIDIA D...

05/08/2025

No Backdoors. No Kill Switches. No Spyware.

NVIDIA GPUs are at the heart of modern computing. They're used across industries - from healthcare and finance to scientific research, autonomous systems an...

31/07/2025

Embark on Epic Adventures in August With a Dozen New Games Coming to GeForce NOW

August brings new levels of gaming excitement on GeForce NOW, with 2,300 titles now available to stream in the cloud. Grab a controller and get ready for epic ...

31/07/2025

Wired for Action: Langflow Enables Local AI Agent Creation on NVIDIA RTX PCs

Interest in generative AI is continuing to grow, as new models include more capabilities. With the latest advancements, even enthusiasts without a developer bac...

29/07/2025

FourCastNet 3 Enables Fast and Accurate Large Ensemble Weather Forecasting With Scalable Geometric ML

FourCastNet3 (FCN3) is the latest AI global weather forecasting system from NVID...

28/07/2025

How New GB300 NVL72 Features Provide Steady Power for AI

The electrical grid is designed to support loads that are relatively steady, such as lighting, household appliances, and industrial machines that operate at con...

24/07/2025

Creative Agency Black Mixture Creates Stunning Visuals With Generative AI Powered by NVIDIA RTX

For media company Black Mixture, AI isn't just a tool - it's an entire p...

24/07/2025

WUCHANG: Fallen Feathers' Lands in the Cloud

Sharpen the blade and brace for a journey steeped in myth and mystery. WUCHANG: Fallen Feathers has launched in the cloud. Ride in style with skateboarding leg...

23/07/2025

Into the Omniverse: How Global Brands Are Scaling Personalized Advertising With AI and 3D Content Generation

In today's fast-evolving digital landscape, marketing teams face increasing ...