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...

20/05/2026

New Nissan Stadium Is First NFL Venue With Permanent Built-In Music Stage

True to the Music City theme, the Tennessee Titans plan to make live music a prominent fixture on game days at the new venue Reflecting the continuing converge...

20/05/2026

NHL Taps Honeywell To Make Arenas, Facilities More Energy-Efficient

The long-term goal is innovation for the next generation of hockey rinks at both the professional and the community level The National Hockey League (NHL) toda...

20/05/2026

A Look Into the Future: What It Takes To Power the Next Generation of Sports Stadiums

End-users and vendors alike work toward cost-effective yet high-quality solution...

20/05/2026

Nasvhvilles New Nissan Stadium To Host Super Bowl LXIV in 2030

The National Football League has announced that Nashville will host Super Bowl LXIV in 2030 at the new Nissan Stadium. The announcement was made at the NFL Spri...

20/05/2026

NFL Awards Minnesota as Host Site of 2028 NFL Draft

The NFL has announced that the 2028 NFL Draft presented by Bud Light will take place in Minnesota, uniting fans from around the world to celebrate one of the mo...

20/05/2026

Lawo Highlights Edge One at InfoComm 2026

As professional AV workflows continue to evolve, expectations around audio, video, networking, and control are rising rapidly. At InfoComm 2026 in Las Vegas, La...

20/05/2026

Haivision to Showcase Video Wall, IPTV, and Ultra-Low Latency Video Innovations at InfoComm 2026

Haivision will showcase its latest innovations at InfoComm 2026, taking place fr...

20/05/2026

Spotify House Returns to CMA Fest With 3 Days of Nonstop Country Music

For the seventh year, Spotify is returning to CMA Fest with Spotify House, the festival's premiere destination for fans. We're taking over downtown Nash...

20/05/2026

Aero 2 from Acustica Audio

Amp-simulation software expanded Acustica Audio's latest release greatly expands on their amp-simulation platform, turning it into a complete amplifica...

20/05/2026

Arturia update the KeyLab Mk3

MainStage integration, Analog Lab improvements & more Arturia have just announced the release of an update that brings an assortment of new features to thei...

20/05/2026

SGL Carbon holds successful Annual General Meeting with strong approval of proposed resolutions

At the Annual General Meeting held on May 20, 2026, the shareholders of SGL Carb...

20/05/2026

From Gulkula to the nation: Yothu Yindi Foundation and NITV deepen national access to Garma Festival

From Gulkula to the nation: Yothu Yindi Foundation and NITV deepen national acce...

20/05/2026

SBS appoints David Fernandez as National Manager, Digital & TV Sales

SBS appoints David Fernandez as National Manager, Digital & TV Sales 20 May, 2026 Media releases SBS has appointed David Fernandez as National Manager, Dig...

20/05/2026

Rohde & Schwarz and INFOZAHYST: A strategic alliance set to redefine modern defense

Rohde & Schwarz and INFOZAHYST: A strategic alliance set to redefine modern defe...

20/05/2026

L3Harris Achieves Major Milestones With Latest Series of Rotating Detonation Engine Tests

A Rotating Detonation Engine being hot fire tested at Purdue University's Zu...

20/05/2026

VAMPIRE Confirms Integrated Capability During Live Exercises

A U.S. Army VAMPIRE system, assigned to Bravo Battery, 1st Battalion, 51st Air Defense Artillery Regiment, 7th Infantry Division/Multi-Domain Command - Pacific ...

20/05/2026

NCAA Tournaments Spark March Madness for Paramount and Warner Bros. Discovery in Nielsen's The Gauge

Cable Captures Only Monthly Increase Among Viewing Categories in March, Earns it...

20/05/2026

The Gauge: Poland | April 2026

April brought a symbolic decrease in the overall time spent in front of television screens. On average, Poles watched video content for 3 hours and 51 minutes a...

20/05/2026

DirecTV Asks FCC to Block Scripps' INYO Acquisition

Share Copy link Facebook X Linkedin Bluesky Email...

20/05/2026

RTS Technology Centre Launches the RTS Technology Awards...

The Royal Television Society Technology Centre today announces the launch of the RTS Technology Awards 2026, celebrating excellence, innovation and achievement ...

20/05/2026

Lightware powers immersive video spectacle for The Hunger...

In the heart of London's financial district, the new purpose-built Troubadour Canary Wharf Theatre invites audiences to experience Suzanne Collins' inte...

20/05/2026

New LiveU LU900Q Powers Record Breaking Broadcast of the...

LiveU, the leader in live IP-video solutions, today announced that production powerhouse BCC Live successfully deployed the new LU900Q intelligent production un...

20/05/2026

Nella Mente di Narciso Docuseries Uses Blackmagic Design Workflow

Nella Mente di Narciso Docuseries Uses Blackmagic Design Workflow Brie Clayton May 19, 2026 0 Comments PYXIS 6K full frame camera and DaVinci Resolve ...

20/05/2026

Beeble launches Canvas, a node-based AI compositor for VFX and Virtual Production pipelinesx

Beeble launches Canvas, a node-based AI compositor for VFX and Virtual Productio...

20/05/2026

DSPolitical and FreeWheel Partner on Political CTV Ads

Share Copy link Facebook X Linkedin Bluesky Email...

20/05/2026

Amazon, Netflix and Google to Capture Half of CTV Ad Market by 2030

Share Copy link Facebook X Linkedin Bluesky Email...

20/05/2026

Roku Introduces 'Creator Hub

Share Copy link Facebook X Linkedin Bluesky Email...

20/05/2026

First Nations Factual Co-production Development Fund launched to elevate Indigenous storytelling in global markets

First Nations Factual Co-production Development Fund launched to elevate Indigen...

20/05/2026

TLC Announces All-Star Comedy Line-Up for Mock the Week: Summer Specials' on TLC

TLC Announces All-Star Comedy Line-Up for Mock the Week: Summer Specials' o...

20/05/2026

'One Hundred Years of Solitude' Concludes This August, With Part Two Premiering on the 5th and the Grand Finale on the 26th

Back to All News One Hundred Years of Solitude Concludes This August, With Part...

20/05/2026

Beloved NHK Dramas to Stream on Netflix Worldwide Starting June 22

Back to All News Beloved NHK Dramas to Stream on Netflix Worldwide Starting June 22 Entertainment 20 May 2026 GlobalJapan Link copied to clipboard Netflix...

20/05/2026

Dolby Recognized as 2025 Supplier of the Year and Overdrive Award Winner by General Motors

May 20 2026, 06:00 (PDT) Dolby Recognized as 2025 Supplier of the Year and Over...

20/05/2026

Two cooks shortlisted for the final of RT Today's TV Home Cook Competition

Mayo's Dee Freney and Margaret Leahy from Galway have reached the final of RT Today's TV Home Cook competition. Both contestants will cook again live...

20/05/2026

RT IN FULL BLOOM AT BORD BIA BLOOM 2026 WITH LIVE BROADCASTS, MUSIC, CHAT AND MUCH MORE

RT IN FULL BLOOM AT BORD BIA BLOOM 2026 WITH LIVE BROADCASTS, MUSIC, CHAT AND M...

19/05/2026

Young Journalist' finalists visit London for training and networking

The winner of Thomson Foundation's Young Journalist of the Year 2025, Tracy Bonareri Onchoke, and runner up Wangu Kanuri enjoyed a three-day trip to London ...

19/05/2026

Cisco and USGA Announce Multiyear Partnership Extension

Cisco and the USGA have announced a multiyear extension of their partnership, which began in 2018. Cisco serves as the Official Technology Partner of the USGA, ...

19/05/2026

Urban Edge Network and Spiideo Partner to Enhance NAIA Sports Streaming

Urban Edge Network (UEN), a streaming platform for NAIA sports, has announced a partnership with Spiideo to provide streaming and production tools to UEN's ...

19/05/2026

Warner Bros. Discovery Announces Expanded Roland-Garros 2026 Coverage

Warner Bros. Discovery (WBD) will provide live coverage of all 900 Roland-Garros matches across its platforms beginning with qualifiers on May 18. In Europe, 21...

19/05/2026

Tubi Launches FIFA World Cup 2026 FOX Hub

Tubi, Fox Corporation's free streaming service, has announced the launch of the FIFA World Cup 2026 FOX Hub, a dedicated destination for World Cup programmi...

19/05/2026

Telefnica and Sony Conduct 5G mmWave Broadcast Trial at Movistar Arena

Telef nica, in collaboration with Sony, has conducted a 5G connectivity trial at the Movistar Arena in Spain using the 26 GHz millimetre wave (mmWave) band. The...

19/05/2026

Ross Production Services Integrates Calrec Argo M into New Hypermax-1 Truck

Ross Production Services (RPS) has installed a Calrec Argo M console into its new Hypermax-1 remote production truck, replacing one of three Argo S consoles pre...

19/05/2026

Panasonic Projector and Display Acquires HIVE Media Control

Panasonic Projector and Display Corporation has announced the acquisition of 100% of the shares of UK-based media technology company Hive Media Control Ltd. (HI...

19/05/2026

Globecast Completes Major Renovation of Singapore Facility

Globecast has announced the completion of a nine-month renovation of its Singapore facility, converting it from a traditional linear broadcast operation into a ...

19/05/2026

Grass Valley Signs Three-Year Enterprise Agreement with Phoenix Broadcast Solutions

Grass Valley has announced a three-year enterprise agreement with Phoenix Broadc...

19/05/2026

Watch Brasil Selects Bitmovin for Streaming Player, Encoder, and Observability

Bitmovin has announced that Watch Brasil, a streaming platform operating across Brazil and Europe since 2018, has replaced its legacy systems with Bitmovin'...

19/05/2026

Ateme and Akamai Power Nepal Premier League Live Streaming

Ateme has announced the migration of Dish Home Nepal's Nepal Premier League (NPL) streaming infrastructure to Ateme's TITAN Live solution deployed on Ak...