
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.
Most recent headlines
05/01/2027
Worlds first 802.15.4ab-UWB chip verified by Calterah and Rohde & Schwarz to be ...
07/10/2026
Dalet, a leading technology and service provider for media-rich organizations, today announced the latest Long-Term Supported (LTS) release of Dalet Flex. Build...
06/09/2026
June 9 2026, 23:00 (PDT) Dolby and MagentaTV Bring Fans Closer to the FIFA Worl...
13/08/2026
LaLiga has renewed broadcast agreements with ESPN and DSports covering Spanish-l...
13/08/2026
Three days of skateboarding competitions, live music, and other programming will...
13/08/2026
Matrox Video will showcase its portfolio of IP and software-defined technologies at IBC2026 (Booth 7.B15, RAI Amsterdam, September 11-14).
The portfolio includ...
13/08/2026
SMPTE will present expert-led sessions, professional workshops, and networking events at IBC2026. The organization will be located in the IBC2026 Owner Pavilion...
13/08/2026
Clear-Com will exhibit at IBC2026 (Stand 10.D29, September 11-14, Amsterdam), showcasing FreeSpeak Cell, Avalon IP Station, updates to Arcadia Central Station, ...
13/08/2026
Advanced Systems Group (ASG) has appointed Eran Binyamin Zeitoun as Senior Techn...
13/08/2026
Miami HEAT, Florida Panthers, Orlando Magic, University of Miami join leading vendors for a day of gameday-production talk in South Florida
The 2026 SVG Venues...
13/08/2026
NBC Sports is producing the Twins-Phillies game alongside the streamer, which is...
13/08/2026
Oracle Cloud Infrastructure (OCI) will exhibit at IBC2026 (Hall 5, Booth 5.A21, September 11-14, Amsterdam), demonstrating cloud-based workflows across low-late...
13/08/2026
Dalet will participate in the IBC2026 Accelerator Media Innovation Programme, co...
13/08/2026
Cox Media Group (CMG) has announced multi-year local broadcast rights agreements...
13/08/2026
J nger Audio will join Fraunhofer IIS and industry partners to showcase a cloud-based, DTV+-compliant workflow at SET Expo 2026 in S o Paulo, August 17-20. DTV+...
13/08/2026
IBC has announced that Olympic Broadcasting Services (OBS) will receive the Inte...
13/08/2026
NESN has partnered with WSBK-TV38 to broadcast Boston Red Sox games on August 17 and 18 over the air, extending the reach of the 24th annual WEEI/NESN Jimmy Fun...
13/08/2026
LiveU and Panasonic LUMIX have announced the Live Anywhere workflow, demonstrated at NAB 2026 and InfoComm 2026 in collaboration with Social180Group. The work...
13/08/2026
Chyron will demonstrate its sports analysis, graphics, remote production, virtual production, and venue control solutions at IBC2026 (Booth 7.A23). This year...
13/08/2026
Ratings Roundup is a rundown of recent ratings news and is derived from press re...
13/08/2026
Season tips off Oct. 20 and runs through April 11; Christmas Day, NBA Cup, All-S...
13/08/2026
Company preview bio-interactive' synthesizer
VAEMI have announced the upcoming launch of a new standalone bio-interactive' generative synthesizer....
13/08/2026
Plug-in host gains new Slot Scenes feature
Ravine DSP have recently updated their innovative plug-in host, kitting it out with a new feature that brings yet...
13/08/2026
New Agreement Aims to Leverage Gracenote Infrastructure to Create More Relevant ...
13/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
13/08/2026
IBC today announced that its most prestigious honour, the International Honour for Excellence (IHFE), will be presented to Olympic Broadcasting Services (OBS), ...
13/08/2026
Dalet, a leading technology and service provider for media-rich organizations, today announced its participation in the IBC2026 Accelerator Media Innovation Pro...
13/08/2026
dzjinius, the all-in-one production management platform for the media and entertainment industry, will showcase its new application, dzjinius on-set , at IBC20...
13/08/2026
Broadcasting Center Europe (BCE), a leading European provider of media services, system integration and product development, will demonstrate an end-to-end sove...
13/08/2026
Clear-Com is returning to IBC 2026, taking place September 11-14 in Amsterdam, Netherlands. At Stand 10.D29, Clear-Com will spotlight the award-winning FreeSpe...
13/08/2026
Test & measurement innovator, Leader Electronics of Europe, will showcase its comprehensive portfolio of Leader, PHABRIX and LeaderPhabrix test and measurement ...
13/08/2026
KRK Brings Advanced Wireless Control to Professional Monitoring With New V Serie...
13/08/2026
Anthony Noack Captures Artist's Journey in Estonia with Blackmagic Design
Brie Clayton August 12, 2026
0 Comments
Solo filmmaker documents concept...
13/08/2026
ARRI Image Science makes its mobile debut in the HONOR Robot Phone
Brie Clayton August 12, 2026
0 Comments
Hero image displays the HONOR Robot Phone, ...
13/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
13/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
13/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
13/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
13/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
13/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
13/08/2026
Suitest's Test Automation Platform Simplifies Video Quality Assurance, Monitoring, and Device Certification Across the OTT Ecosystem
At IBC2026, Suitest, a...
13/08/2026
Cinegy GmbH, the premier provider of software-defined television technology, will have its key software solutions ready to demonstrate at SET Expo 2026 (18 20...
13/08/2026
Scripps Research has established the Peter K. Vogt Endowed Chair, a new faculty ...
13/08/2026
LA JOLLA, CA-A vaccine's molecular structure plays a key role in determining how the immune system responds and prepares to protect the body from future exp...
13/08/2026
Venera Technologies Showcases AI-Powered Innovations Across its Media QC Platfor...
13/08/2026
New U and U&W Documentary Features Kathleen Richards, One of the Last Surviving Witnesses to Fred and Rose West
Kathleen is Reunited with Childhood Friend and ...
13/08/2026
Thursday 13 August 2026
Official trailer released for the return of Tea with Ju...
13/08/2026
Dalet, a leading technology and service provider for media-rich organizations, t...
13/08/2026
Wenvoe serves over 1 million people across South Wales
13 August 2026, Winchester, UK - Vale of Glamorgan MP, Kanishka Narayan, has praised the engineering exp...
13/08/2026
RT 's Miriam O'Callaghan welcomed a range of specially invited guests to the National Concert Hall last week for a unique event to mark a new season wit...