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 ...

07/10/2026

Dalet Flex LTS Delivers Smarter Media Operations from Ingest to Distribution

Dalet, a leading technology and service provider for media-rich organizations, today announced the latest Long-Term Supported (LTS) release of Dalet Flex. Build...

09/09/2026

IBC 2026: Sony Introduces SEL814G Fisheye Zoom G Lens

Sony Electronics has announced the SEL814G, the company's first fisheye zoom G Lens for full-frame Alpha E-mount cameras. The lens will be available in Octo...

09/09/2026

IBC 2026: Telestream Expands Practical AI Capabilities Across Vantage and UP Platform

Telestream has announced an expansion of its Practical AI capabilities across th...

09/09/2026

IBC 2026: Chyron and Haivision Announce Camera-to-Cloud Live Production Integration

Haivision and Chyron have announced a technology partnership integrating Haivisi...

09/09/2026

ManningCast Reveals 2026-27 Season Schedule with Heist Mini Movie

Omaha Productions has released ManningCast: Heist, a short film featuring Peyton and Eli Manning attempting to break into NFL Commissioner Roger Goodell's o...

09/09/2026

IBC 2026: Imagine Communications to Showcase XVR Updates

Imagine Communications will demonstrate the next evolution of XVR at IBC2026 (Stand 1.B73, RAI Amsterdam, September 11-14). XVR is Imagine's channel-in-a-b...

09/09/2026

IBC 2026: swXtch.io Launches AI Broadcast Orchestration Tool abbe

swXtch.io has announced abbe, an AI-based orchestration layer for live media workflows, making its world premiere at IBC2026 (Meeting Room 5.MR13, Hall 5, Septe...

09/09/2026

Inside the NFL Returns to X for Second Season, Marking 50th Anniversary

NFL Films has announced the second season of Inside the NFL on X as an X Original, premiering Wednesday, September 9. The series marks Inside the NFL's 50th...

09/09/2026

LiveU Expands AP Partnership with LU900Q Fleet and MAM Integration

LiveU has announced an expanded partnership with The Associated Press, deploying the largest fleet of LU900Q intelligent production units in the industry as par...

09/09/2026

Diversified to Consolidate New Jersey Operations into New Newark Facility

Diversified has announced plans to consolidate its four existing New Jersey locations into a new facility in Newark, expected to be fully operational by the end...

09/09/2026

IBC 2026: Wisycom Showcases MATF Antenna Matrix, PFL RFoF Box, and MPR60 Updates

Wisycom will exhibit new RF products at IBC2026 (Stand 8.D60, September 11-14), including the MATF Wideband Antenna Matrix, PFL Portable RF over Fiber Box, and ...

09/09/2026

IBC 2026: G&D and VuWall to Introduce vsNEO KVM-over-IP Platform

Guntermann & Drunck (G&D) and VuWall, both Panoptec companies, will introduce vsNEO at IBC2026 (Stand 8.B63, September 11, RAI Amsterdam). Pre-orders open in ea...

09/09/2026

Mo-Sys Completes Restructuring, Promotes Selin Kemal to Managing Director

Mo-Sys has completed a business restructuring and relocated to a new facility in Canada Water, London. As part of the reorganization, Selin Kemal has been promo...

09/09/2026

Aicox and TAG Video Systems Power Monitoring for Telefnicas TSAmediaHUB

Aicox has integrated TAG Video Systems' Core monitoring platform into Telef nica's TSAmediaHUB audiovisual contribution and distribution infrastructure....

09/09/2026

IBC 2026: Blackmagic Design Releases DaVinci Resolve 21.1

Blackmagic Design has released DaVinci Resolve 21.1, a free update available now through the Blackmagic Design website. The release adds new AI tools, workflow ...

09/09/2026

ESPN and Apple Music Collaborate on Monday Night Football Music Curation for 2026-27 Season

ESPN and Apple Music have announced a collaboration on music curation for Monday...

09/09/2026

Sacramento Production Services Deploys Wisycom RF System at Sutter Health Park

Sacramento Production Services has completed a wireless audio overhaul at Sutter Health Park, home of the Athletics during their three-year residency in Sacrame...

09/09/2026

NDI and NVIDIA Collaborate on AI-Powered Multilingual Content Workflows

NDI and NVIDIA have announced a collaboration to develop AI-powered workflows enabling broadcasters to create and distribute multilingual content from a single ...

09/09/2026

Sports Broadcasting Hall of Fame Announces the Class of 2026

Christopher Chip Adams, Troy Aikman, Jim Dove, Jim Eady, Bucky Gunts, Robert A. Iger, Charlie Jablonski, Robert Kraft, Tom Rinaldi, and Dick Stockton to be ho...

09/09/2026

NBC Sports Opens 21st SNF Season With Expanded Schedule, Traveling Studio Show, and Bulked Up Toolkit

ND2 returns as the primary unit, While FNIA gets SSQC and new flexible Rover...

09/09/2026

Celemony Tonalic gains additional Paul Kleber upright bass

New parts aimed at hip-hop and pop productions The latest update to Celemony's innovative virtual session musician expands the collection of built-in in...

09/09/2026

Sonarworks Autumn Sale

Save up to 40% until 21 September 2026 Sonarworks are currently running their Autumn Sale, with discounts of up to 40% currently available across their rang...

09/09/2026

Bjooks Beat Gems to begin shipping

Upcoming title officially launches in September 2026 Bjooks' celebrations for this year's 909 Day will be welcome news amongst drum machine lovers, ...

09/09/2026

NITV to bring First Nations netball to audiences nationwide

NITV to bring First Nations netball to audiences nationwide 9 September, 2026 Media releases Every match of the 2026 First Nations Tournament will be live ...

09/09/2026

NFVF CALL FOR PROPOSALS: YOUTH FILMMAKER PROJECT FACILITATING COMPANY 2026

The National Film and Video Foundation (NFVF) invites eligible Tier 1 and 2 South African production companies to submit proposals to serve as the Facilitating ...

09/09/2026

Nielsen launches CTV Ad spend data into its Italian Ad Intel product

Italy launch follows UK and Germany as Nielsen expands product across EMEA Milan, Italy, September 9, 2026 - Nielsen, a global leader in audience measurement, ...

09/09/2026

Gracenote Expands AI Product Roadmap with Sports MCP Server, Entertainment SLM and Agents

Planned solutions tackle accuracy, cost and latency barriers to deploying AI at ...

09/09/2026

Dalet Promotes Brian Doheny to CEO

Share Copy link Facebook X Linkedin Bluesky Email...

09/09/2026

Studio Technologies Expands StudioComm Monitoring With In...

Studio Technologies, a leading manufacturer of high-quality audio, video, and fiber-optic solutions, introduces its new Model 791 Control Console at IBC 2026 (N...

09/09/2026

Maxon Brings Exclusive Preview of Fall Innovations to IBC...

Maxon, maker of powerful, approachable software solutions for creators working in 2D and 3D design, motion graphics, visual effects and visualization, is headin...

09/09/2026

NUGEN Audio Leads the Dialog Intelligibility Conversation...

NUGEN Audio unveils DialogCheck v1.2, the latest evolution of its intelligent dialog intelligibility and compliance tool, at IBC 2026 (Pod P27). With a sharpene...

09/09/2026

Trusted Partner Network Launches Fix It or Risk It to Hel...

Trusted Partner Network Launches Fix It or Risk It to Help the Entertainment Industry Tackle Everyday Security Risks Industry-Wide Campaign Launches at IBC2...

09/09/2026

FCC to Vote on Opening Up Spectrum for Satellite, IoT

Share Copy link Facebook X Linkedin Bluesky Email...

09/09/2026

NDI, NVIDIA Collaborate On Real-Time AI Multilingual Content

Share Copy link Facebook X Linkedin Bluesky Email...

09/09/2026

83 percent of UK advertisers are using AI but speed and n...

AI has moved firmly beyond experimentation in UK advertising, with more than eight in ten marketers (83%) now actively using or piloting AI in production, accor...

09/09/2026

Pixitmedia by DataCore to showcase cloud and connected pr...

IBC2026 - Stand 7.D22 At IBC2026, Pixitmedia by DataCore will showcase its latest capabilities designed to simplify distributed production, accelerate workflow...

09/09/2026

Net Insight Showcases Open Live Media for Controlled Live...

Stockholm, Sweden September 9th, 2026 At IBC2026, on booth 1.B47, Net Insight will showcase Open Live Media, its architecture for delivering resilient live ...

09/09/2026

Net Insight and DMC expand repeatable remote production m...

Net Insight today announced that DMC Production Norway is continuing the use of its Open Live Media technology for premium European football, deploying Nimbra 5...

09/09/2026

Amagi to Showcase Four AI-Native Innovations Built to Pow...

Amagi, the media industry cloud platform for unified broadcast, streaming, and monetization, will showcase four new AI-native capabilities at IBC2026, Hall 5, S...

09/09/2026

Limecraft Brings Connected Automated and Intelligent Medi...

Limecraft today announces version 2026.6 of its AI-powered production platform, extending capabilities for connected media operations. An AI-assisted approach t...

09/09/2026

Telestream Advances Practical AI from Content Understandi...

Telestream, a global leader in media workflow technologies, today announced the next evolution of its Practical AI strategy, evolving its comprehensive portfoli...

09/09/2026

Dalet Appoints Brian Doheny as Chief Executive Officer

Dalet, a leading technology and service provider for media-rich organizations, today announced the appointment of Brian Doheny as Chief Executive Officer (CEO)....

09/09/2026

LiveU Offers Starlink for News and Sports Broadcast as Cl...

LiveU is now a Clarus Integrated Reseller, bringing Starlink's fast, reliable broadband directly into LiveU's cellular bonding EcoSystem through a singl...

09/09/2026

Study: New Streaming TV Series Orders Plumet

Share Copy link Facebook X Linkedin Bluesky Email...

09/09/2026

G&D, VuWall To Introduce vsNEO KVM Platform At IBC2026

Share Copy link Facebook X Linkedin Bluesky Email...

09/09/2026

FCC May Ramp Up Regulation of How Broadcasters Cover Polls

Share Copy link Facebook X Linkedin Bluesky Email...

09/09/2026

Avid to Demo New Avid Content Core Features at IBC2026

Share Copy link Facebook X Linkedin Bluesky Email...

09/09/2026

Wisycom Showcases Latest Innovations at IBC 2026

Wisycom is showcasing the latest additions to its ecosystem of professional RF technologies at IBC 2026 (Stand 8.D60). This includes its new MATF Wideband Anten...

09/09/2026

VisualOn and Cires21 Cut Delivery Bitrate Up to 76 Percen...

AMSTERDAM, IBC2026 VisualOn, Inc. and Cires21 today released an updated joint whitepaper at IBC 2026 demonstrating measurable, high-impact improvements in visu...