Sony Pixel Power calrec Sony

How Deep Learning Is Aiding Preservation of Seneca and Other Endangered Languages

03/01/2019

Linguists estimate that at least half of the world's estimated 7,000 spoken languages will become extinct by the century's end, due to forces ranging from globalization to cultural assimilation.

Part of the challenge of documenting and revitalizing endangered languages is a lack of texts and speech recordings to work with. Seneca, a language of one of the six Iroquois Nations in North America, has only about 100 first-language speakers and several hundred more second-language learners.

Automatic speech recognition (ASR) technology is widely used to transcribe languages with millions or billions of speakers, like English and Mandarin. But it has only scratched the surface with languages like Seneca, which have vastly fewer speakers and significantly less data to work with.

Now a team of researchers at the Rochester Institute of Technology in New York, along with colleagues from the University at Buffalo, is tapping deep learning to bolster the ability of ASR. And while its focus is on Seneca, the project's vision encompasses the preservation of languages globally as well as an important part of our shared cultural history.

Knowing about different languages teaches us a lot about how our brain works, said Emily Prud'hommeaux, an assistant professor of computer science at Boston College and a research faculty member at RIT. When you document a language, you're preserving information not only about that language but also about how humans use language in general.

It's no coincidence that Prud'hommeaux and her team started with the Seneca language. Three members of the Seneca nation are part of the effort - a direct connection that is rare in research of this type, she said.

Leading the charge is Robbie Jimerson, a Ph.D. student in RIT's Golisano College of Computing and Information Science. He is a member of the Seneca Nation of Indians and is passionate about ensuring the survival of the Seneca language.

There's a big effort by the leaders of the tribe to preserve and promote our language, said Jimerson. I was looking for an opportunity to contribute.

Using GANs to Create More Language Samples Now in its third year, the project has had challenges when it comes to accumulating language data. Jimerson said the Seneca community can be guarded about what it shares with other people, so there wasn't an abundance of recordings of the language being spoken. He set out to change that.

He started by recording friends and elders who speak the language and asking them to record their friends. He found out whenever someone was speaking Seneca in public. He asked for family recordings of elders telling stories handed down from previous generations. And he grabbed any publicly available videos or recordings he could find online.

The team has fine-tuned an ASR model for Seneca, running it through generative adversarial networks to create more samples out of the limited number of recordings. The model turns wave files of the spoken language into streams of characters, while computing probability and making corrections.

The resulting data is fed into a deep learning model that in turn expands upon the ASR model's accuracy.

The team's networks run in two compute settings: on a nine-server machine learning lab running a variety of NVIDIA Tesla GPUs, and on a university cluster of large servers, each running 10 NVIDIA Tesla P4 GPUs. Each cluster runs a range of deep learning frameworks such as TensorFlow and Caffe.

The computer engineering cluster is for all students in the computer engineering department, and so they have to compete' for these resources, said Ray Ptucha, assistant professor of computer engineering at RIT, another collaborator on this project.

With access to these clusters at a premium, Jimerson tests code and checks the stability of models on a local machine running an NVIDIA TITAN X rather than inconvenience other students by running a model that might crash.

Achieving Better Accuracy So far, the team's efforts have brought the word error rate of its ASR model from 70 percent down to 56 percent. The goal, said Prud'hommeaux, is to get that rate down to 25 percent, which is where ASR systems were in processing English several years ago.

The more samples of spoken and written Seneca the team can accumulate, the more the error rate will decrease. (Today, English ASR models can achieve word error rates as low as 5 percent.)

The team's work is expected to help with language preservation efforts around the world.

Prud'hommeaux said the team has an agreement with an archiving institution that's a condition of a grant the project received from the National Science Foundation. The resulting language archiving database will be made available as a resource for other efforts seeking to document threatened languages.

Additionally, Prud'hommeaux said the team's work could prove helpful for any deep learning effort that has to make do with limited amounts of data.

Read more about the team's work in their research papers here and here.

Feature image: The Haudenosaunee (Iroquois Confederacy) flag, via Wikimedia Commons.
LINK: https://blogs.nvidia.com/blog/2019/01/02/deep-learning-preserves-senec...
See more stories from nvidia

Most recent headlines

05/01/2027

Worlds first 802.15.4ab-UWB chip verified by Calterah and Rohde & Schwarz to be demoed at CES 2026

Worlds first 802.15.4ab-UWB chip verified by Calterah and Rohde & Schwarz to be ...

04/08/2026

Dalet Announces Commercial Availability of Dalia, Bringing Media-Aware Agentic AI to Enterprise Productions

Dalet, a leading technology and service provider for media-rich organizations, t...

04/07/2026

Detective Conan: Fallen Angel of the Highway Opens in Dolby Cinemas Across Japan, Presented in Dolby Atmos and Dolby ...

April 7 2026, 19:00 (PDT) Detective Conan: Fallen Angel of the Highway Opens in...

01/06/2026

Dolby Sets the New Standard for Premium Entertainment at CES 2026

January 6 2026, 05:30 (PST) Dolby Sets the New Standard for Premium Entertainment at CES 2026 Throughout the week, Dolby brings to life the latest innovatio...

02/05/2026

Dalet Flex LTS Delivers Smarter Search, Faster Editing, and an AI-Ready Foundation for Modern Media

Dalet, a leading technology and service provider for media-rich organizations, t...

01/05/2026

NBCUniversal's Peacock to Be First Streamer to Integrate Dolby's Full Suite of Premium Picture and Sound Innovations

January 5 2026, 18:30 (PST) NBCUniversal's Peacock to Be First Streamer to ...

14/04/2026

ToolsOnAir and Omnistream Bring Mobile SRT Contribution into Professional 24/7 Playout and Live News Workflows

ToolsOnAir and Omnistream Bring Mobile SRT Contribution into Professional 24/7 P...

14/04/2026

NAB 2026: Haivision Launches Falkon X4 5G Mobile Video Transmitter

Haivision has announced the Falkon X4, a 5G mobile video transmitter for live broadcast and remote production. The device will be showcased at NAB Show 2026. ...

14/04/2026

SVG New Sponsor Spotlight: Stripe TVs Matthew Pavey on Making Live-Production Tech More Portable, Intuitive, and Accessible

Founded by veterans of the production-truck world, Stripe TV was born out of a d...

14/04/2026

Studio Berlin Adds LDX 135 and LDX 180 Camera Systems from Grass Valley

Grass Valley has expanded its partnership with Studio Berlin, supplying 12 LDX 135 UHD/HDR camera systems and 12 LDX 180 Super 35mm cinematic cameras, including...

14/04/2026

LTN Appoints Mark Romano and Edward Cox to Vice President Roles

LTN has announced two senior appointments ahead of NAB Show 2026: Mark Romano as Vice President, Multichannel Platforms, and Edward Cox as Vice President, Sales...

14/04/2026

Agor and Sennheiser to Deploy Largest Spectera System to Date at Eurovision Song Contest 2026

Sennheiser and Italian rental company Agor have begun preparations for their Eu...

14/04/2026

DAZN and ADI Predictstreet Announce Prediction Market Partnership Ahead of FIFA World Cup 2026

DAZN and ADI Predictstreet have announced a partnership to integrate ADI Predict...

14/04/2026

Deltatre Completes Digital Platform for Serie A as Part of Four-Season Partnership

Deltatre has announced the completion of a direct-to-fan website and app for Leg...

14/04/2026

NAB 2026: Daktronics to Exhibit with Grass Valley

Daktronics, will exhibit at NAB Show 2026 in partnership with Grass Valley at Booth C2408, Las Vegas Convention Center, April 19-22. Daktronics will showcase a...

14/04/2026

NAB 2026: Backblaze to Host Partner Showcases

Backblaze will host a series of partner presentations at NAB Show 2026 (Booth N1259, North Hall), open to all exhibition hall badge holders. Showcase partners i...

14/04/2026

NAB 2026: BRAHMA AI to Exhibit Enterprise AI Content Platform

BRAHMA AI will exhibit at NAB Show 2026 (Booth W2415, West Hall), demonstrating its Enterprise AI Content Platform for media, entertainment, sports, and technol...

14/04/2026

Bridge Technologies VB440 Integrated into NEP Platform

Bridge Technologies has announced that its VB440 production probe has been integrated into NEP Platform, NEP Group's software orchestration system. The inte...

14/04/2026

NAB 2026: Clear-Com to Demonstrate Expanded Intercom Ecosystem

Clear-Com will introduce new products and demonstrate its communications ecosystem for broadcast and live production at NAB Show 2026 (Booth C5807, April 19-22)...

14/04/2026

NAB 2026: EZDRM to Introduce Revenue Security Prism Framework

EZDRM will use NAB Show 2026 (Booth W2260) to introduce the Revenue Security Prism, a framework for combining multiple security technologies to protect streamin...

14/04/2026

NAB 2026: Telos Alliance Product Preview

Telos Alliance will introduce the following products at NAB Show 2026: TV and Media Telos Infinity MK2 Panels: A new generation of hardware control panels for...

14/04/2026

NAB 2026: Panasonic to Showcase IP and IT Production Solutions

Panasonic Video and Audio Systems North America will exhibit at NAB Show 2026 (Booth C3509), demonstrating IP- and IT-based production solutions for sports, bro...

14/04/2026

Behind the Mic: WNBA Adds Sue Bird, Sophie Cunningham to Networks Commentary Teams; John Buccigross Signed to ESPN Extension

Behind The Mic provides a roundup of recent news regarding on-air talent, includ...

14/04/2026

NAB 2026: Blackmagic Design Announces Multiple New Products

Blackmagic Design will exhibit at NAB Show 2026 (Booth N2502). CEO Grant Petty s product announcement livestream is available at youtube.com. The company announ...

14/04/2026

Thomas Riedel Acquires ARRI, Adding Camera and Lighting Component to Riedel Group Portfolio

The deal establishes a close strategic alignment' between the iconic cinema...

14/04/2026

Taming the Untamed: Producing the 2026 Absa Cape EPIC Mountain-Bike Race

BIGSHOT Media, with support from Teradek, produced untamed African mountain-bike race' with daily coverage and highlights show The 2026 Absa Cape EPIC, an...

14/04/2026

SVG Announces Sports AI Innovation Lab to Advance the Use of AI in Live Production

The Sports Video Group (SVG) today announced the launch of the SVG AI Innovation...

14/04/2026

AIR Music Tech release Fabric Vintage Synths Vol.1

Captures a trio of renowned polysynths The latest software to join AIR Music Tech's extensive catalogue captures the sound of three sought-after polysyn...

14/04/2026

United Plugins introduce UnitedFreeBundle

Free offering includes 10 powerful plug-ins United Plugins have announced the launch of a new bundle that brings together 10 of their pro-audio plug-ins, an...

14/04/2026

Celemony update Tonalic

Julian Coryell joins virtual session player line-up Announced at NAMM 2026, Celemony's Tonalic kits DAW users out with real performances by world-class ...

14/04/2026

Supporting Safe Space Flights with WESCAM MX-Series Imaging Systems

WESCAM MX -Series EO/IR Systems Provide Critical Visibility During NASA Re-Entry Operations....

14/04/2026

L3Harris Demonstrates Autonomous Electronic Warfare Capability During US Army Experiment

DiSCO reduces uncertainty during the fog of war in modern threat environments an...

14/04/2026

GOES-19 One Year Later: Protecting Communities Through Advanced Technology

GOES-19 imagery captured by L3Harris-built Advanced Baseline Imager technology helps forecasters issue life-saving weather warnings. Credit: NOAA/NASA...

14/04/2026

Reimagining Earth Measurement for the AI Era: L3Harris and Xoople Develop a New Spacebourne Capability

For decades, understanding the physical world from space has required a trade-of...

14/04/2026

Nielsen Appoints Roberto Ruiz to Lead Measurement Science

Ruiz has helped fuel growth for both client-side and media companies, including, most recently, TelevisaUnivision. He will spearhead transformation, innovatio...

14/04/2026

LTN Appoints Mark Romano, Edward Cox to Leadership Positions

Share Copy link Facebook X Linkedin Bluesky Email...

14/04/2026

Grass Valley Adds Telestream Vantage, Pulse and UP to AMPP

Share Copy link Facebook X Linkedin Bluesky Email...

14/04/2026

XenData Announces Backup, Archive and Cloud-Connect for LucidLink

Share Copy link Facebook X Linkedin Bluesky Email...

14/04/2026

Thomas Riedel Acquires ARRI

Share Copy link Facebook X Linkedin Bluesky Email...

14/04/2026

Shotoku Introduces the World to Aura P2 PTZ Prompter Pann...

Shotoku Introduces the World to Aura P2 PTZ Prompter Panner at NAB 2026 New system removes PTZ pan restrictions for teleprompter-based productions Shotoku US...

14/04/2026

Telestream and Grass Valley Connect Live and File-Based W...

Integration of Vantage, Pulse, and Telestream UP with Grass Valley AMPP Ecosystem enables scalable, interoperable workflows spanning live production and file-ba...

14/04/2026

Dalet Appoints Brian Doheny as President and Chief Revenu...

Enterprise growth leader to scale Dalet's next phase of innovation and global expansion New York, NY April 14, 2026 Dalet, a leading technology and ser...

14/04/2026

Berklee Celebrates Prince's Legacy in Two-Night Signature Series Event

Berklee Celebrates Prince's Legacy in Two-Night Signature Series Event Directed by Tia Fuller, the Prince Project (April 16-17) brings together more than ...

14/04/2026

Arooj Aftab Is Anything but Predictable

Arooj Aftab Is Anything but Predictable The singular artist explores the juxtaposition of grief and joy, dark and light, in her distinctive sound. April 14, ...

14/04/2026

Appear Expands X Platform from Core to Edge at NAB Show 2...

Appear launches include XM estate management and new X Platform processing enhancements to add density for next-generation hybrid & IP workflows, X5 is also now...

14/04/2026

Synamedia turns OTT content into TikTok-style feeds with...

Addressing the needs of a new generation's viewing habits, Synamedia launches GO Shorts. The AI-powered module turns existing catalogues into TikTok-style ...

14/04/2026

NAB 2026 - Vubiquity and Eluvio Showcase Streaming Soluti...

Vubiquity, an Amdocs company and global leader in technology-led media services, will be showcasing a new end-to-end streaming solution in collaboration with El...

14/04/2026

LiveU Announces Expanded Collaboration with Sony at NAB S...

LiveU today announced a significant expansion of its collaboration with Sony Corporation, introducing integrated support for Sony's file-based workflow solu...

14/04/2026

BBC World Service TV selects Open Broadcast Systems for I...

Open Broadcast Systems (https://www.obe.tv/) has announced that BBC World Service has selected its decoders for IP Television distribution. The high-quality, lo...

14/04/2026

Blackmagic Design Announces DaVinci Resolve 21

Blackmagic Design Announces DaVinci Resolve 21 Brie Clayton April 14, 2026 0 Comments Major update adds new Photo page bringing Hollywood's most a...