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...

07/05/2026

New Nielsen Report Shows The Profound Impact of Asian Influence on Sports and Pop Culture

Alysa Liu and Shohei Ohtani Help Drive Viewership as 91 of the Top 100 Broadcast...

07/05/2026

IAB Tech Lab Introduces Standardized Signals For CTV Ad Portfolio

Share Copy link Facebook X Linkedin Bluesky Email...

07/05/2026

Cobalt Digital Wins Two Future Best of Show Awards at 202...

Cobalt Digital Wins Two Future Best of Show Awards at 2026 NAB Show Manufacturer Recognized by TV Tech and TVBEurope for Innovation in signal processing Cobal...

07/05/2026

FOR-A delivers creativity practicality and technical exce...

Software and hardware platforms, AI power and user-friendliness on show...

07/05/2026

Intinor brings advanced IP transport diagnostics and HDR...

Intinor will demonstrate its latest technical enhancements for the Direkt series at BroadcastAsia 2026. With a continued focus on reliable contribution and remo...

07/05/2026

Bitmovin Powers Global Film Streaming Platform MUBI

Bitmovin has announced that MUBI has chosen Bitmovin as its cloud VOD encoding partner, replacing MUBI's legacy on premises encoding setup to improve scalab...

07/05/2026

Meet Graduates from Berklees Class of 2026

Meet Graduates from Berklees Class of 2026 Members of this years graduating class reflect on their proudest moments at Berklee and look ahead to whats next. ...

07/05/2026

Convergence is Now Established Reality,' Says NAB 2026 Report

Share Copy link Facebook X Linkedin Bluesky Email...

07/05/2026

Interra Systems to Showcase Best in Class QC Monitoring a...

At BroadcastAsia 2026, Interra Systems will demonstrate its latest innovations in automated quality control (QC), real-time monitoring, and captioning. The comp...

07/05/2026

PlayBox Neo shines a spotlight on delivering Secure Scala...

At this year's Broadcast Asia, PlayBox Neo is set to unveil recent innovations across its PlayBox Neo Suite and integrated range of broadcast media solution...

07/05/2026

BFBS selects Synamedia to deliver New Digital Platform fo...

Strategic three-year partnership marks delivery phase of BFBS' next-generation media vision Media organisation and military charity BFBS (British Forces Br...

07/05/2026

Amagi Unlocks New Opportunities for CTV Performance with...

Amagi, the agentic industry cloud platform for unified broadcast, streaming, and monetization, today announced the availability of its In-Content Ads offering v...

07/05/2026

Lightware Introduces Rack Taurus For Clean Centralized AV...

Lightware Visual Engineering has developed Rack Taurus for rack-based environments such as education and corporate training spaces. It enables clean and simple ...

07/05/2026

Jigsaw24 Showcases End-to-End Media Workflows at MPTS 202...

Jigsaw24, the UK's leading media equipment supplier and systems integrator, will showcase its expanded end-to-end workflow capabilities at MPTS 2026, signal...

07/05/2026

Ease Live Granted US Patent for Technology Powering Perfe...

Ease Live, an Evertz company, today announced that it has been granted a US Patent for its proprietary graphical overlay technology, the foundation for interact...

07/05/2026

Leader prepares advanced Test and Measurement showcase fo...

Test & measurement innovator Leader Electronics of Europe will present an extensive range of Leader, PHABRIX and LeaderPhabrix test and measurement solutions at...

07/05/2026

LiveU Signals a New Era of Live Broadcasting at Broadcast...

At Broadcast Asia 2026 (Stand 5H3 8), LiveU is redefining live production with its most powerful IP-video EcoSystem to date built to help broadcasters and con...

07/05/2026

Colorfront Streaming Server Awarded Trusted Partner Network Gold Logo Certification

January 8, 2024 Colorfront (colorfront.com), a leader in high-performance, on-s...

07/05/2026

Colorfront Unleashes New Opportunities for Content Owners Plus Other Ground-Breaking Visual Experiences at Nab 2024

March 20, 2024 NAB 2024, Las Vegas - Colorfront (colorfront.com), the multi-awa...

07/05/2026

Colorfront Delivers Innovations for HDR Cinema at Cinemacon 2025

April 1, 2025 CINEMACON, APRIL 1, 2025 - Colorfront (colorfront.com), the multi-award-winning developer of high-performance dailies/transcoding/streaming syste...

07/05/2026

Colorfront to Showcase Advanced HDR Cinema Mastering Solutions at CineEurope 2025

June 15, 2025 Colorfront (colorfront.com), an Academy and Emmy Award-winning de...

07/05/2026

Colorfront at ICTA Barcelona Cinema Technology Summit

June 15, 2025 Colorfront participated in the ICTA Barcelona Cinema Technology Summit on Sunday, June 15, 2025. Held at The Phenomena Experience, the event feat...

07/05/2026

Colorfront Does IBC 2024 Live From Stockholm!

July 1, 2025 Colorfront (colorfront.com), the multi-award-winning developer of high-performance dailies/transcoding/streaming systems for motion pictures, OTT,...

07/05/2026

Colorfront Transkoder Delivers a Masterful Performance at Annapurna Studios

July 1, 2025 Passion and dedication will take you places. Come with us on a short trip to the heart of India, where Annapurna Studios is living-up to the inspi...

07/05/2026

Colorfront Opens a New Chapter in Color Tools For Cinema & Television

July 3, 2025 Colorfront (colorfront.com), the multi-award-winning developer of high-performance dailies/transcoding/streaming systems for motion pictures, OTT,...

07/05/2026

Colorfront at IBC 2025: Advanced Tools Make Easy Work of Critical Mastering Tasks and More!

September 1, 2025 IBC 2025, Amsterdam - Colorfront (colorfront.com) - the Acade...

07/05/2026

Colorfront Introduces Colorfront Immersive Utility, a New Mac App for Creating Apple Immersive Video

April 17, 2026 LOS ANGELES - April 17, 2026 - Colorfront today announced Colorf...

07/05/2026

Colorfront Delivers Even More AI Automation Power and Extends Technology Partnerships with Dolby Apple

April 23, 2026 NAB 2026, Las Vegas - the Academy and Emmy Award-winning develop...

07/05/2026

CNN Founder Ted Turner Dies at 87

Share Copy link Facebook X Linkedin Bluesky Email...

07/05/2026

FCC Urges Appeals Court to Toss Challenges to Nexstar-Tegna Deal

Share Copy link Facebook X Linkedin Bluesky Email...

07/05/2026

Carr Announces FCC Staff Promotions

Share Copy link Facebook X Linkedin Bluesky Email...

07/05/2026

Recreating the 1974 Doctor Who Time Tunnel in After Effects

Recreating the 1974 Doctor Who Time Tunnel in After Effects Graham Quince May 6, 2026 0 Comments The Time Tunnel from Doctor Who titles is one of th...

07/05/2026

Well known Irish faces pushed to the edge in new series of Uncharted with Ray Goggins

Well known Irish faces pushed to the edge in new series of Uncharted with Ray G...

07/05/2026

Powerful four generation story A Traveller Family airs on RT One and RT Player this Monday night

RT will premiere A Traveller Family, a compelling new documentary exploring the...

07/05/2026

Linked and Loaded: Gaijin Single Sign-On Now Available on GeForce NOW

Less typing, more tanking. Faster logins mean more time in the gaming action - and this week provides GeForce NOW members with a smoother path straight into th...

06/05/2026

Wisycom RF Solutions Support Gravity Medias Live Cycling and Marathon Broadcasts

Gravity Media Chief RF Communications Engineer Glenn Willems uses Wisycom RF over Fiber and wireless solutions across major cycling events and international mar...

06/05/2026

Sennheiser Spectera Module Now Available in Bitfocus Companion and Buttons

A Sennheiser Spectera module is now available in Bitfocus Companion and Buttons, enabling direct integration of Spectera with the two software platforms. The mo...

06/05/2026

Ted Turner, Cable Television Pioneer, Sports Broadcasting Hall of Famer, Dead at 87

Ted Turner, the visionary media entrepreneur whose appetite for disruption helpe...

06/05/2026

FIFA World Cup 2026: Peacock Launches Visin de Campo (aka Pitchside Live), Will Stream All 104 Matches in Spanish

Peacock is going all-in on the beautiful game - streaming all 104 FIFA World Cup...

06/05/2026

NoiseWorks Audio launch VoiceAssist Basic, Standard & Advanced

New pricing tiers for vocal/dialogue restoration tool NoiseWorks Audio's AI-powered vocal and dialogue processing plug-in is now available in three diff...

06/05/2026

RME TotalMix FX 2 now available

Popular mixing & routing software overhauled Following a recent public beta test, RME have launched the final release version of the powerful mixing and rou...

06/05/2026

Focusrite: Designing The ISA C8X Audio Interface

New SOS Video Feature Focusrites ISA C8X is a milestone product that brings together the companys analogue heritage and their expertise in digital audio. Yo...

06/05/2026

L3Harris to Boost Polish Navy Combat Power with Advanced Ship System

Polands Miecznik-class frigates are part of the largest contract in Polish shipbuilding history. (Image Credit: PGZ Stocznia Wojenna)...

06/05/2026

FCC's Anna Gomez Urges Rigorous Review of Paramount-WBD Merger

Share Copy link Facebook X Linkedin Bluesky Email...

06/05/2026

Riedel Ups Marc Engroff to CFO, Shifts Frank Eischet to Group COO

Share Copy link Facebook X Linkedin Bluesky Email...