
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 ...
04/08/2026
Dalet, a leading technology and service provider for media-rich organizations, t...
04/07/2026
April 7 2026, 19:00 (PDT) Detective Conan: Fallen Angel of the Highway Opens in...
05/06/2026
The university-wide initiative has pushed their creative content to a new level
Although collegiate athletics at a single institution can contain numerous spo...
05/06/2026
In-venue and creative video staffers at the professional and collegiate level ha...
05/06/2026
Synamedia has announced that Lumine Group has agreed to acquire its Video Network business. The company is positioning the transition as the start of a new phas...
05/06/2026
Ateme, Broadcasting Center Europe (BCE), and Scaleway have announced a strategic partnership to deliver a cloud-based media supply chain covering ingest through...
05/06/2026
Audinate has announced three new additions to its Dante AVIO Install adapter series: a 4-Channel Analog Input, a 4-Channel Analog Output, and a 2-Ch In/2-Ch Out...
05/06/2026
Sportradar Group AG has announced a multi-year extension of its exclusive global...
05/06/2026
The M6 Group will broadcast FIFA World Cup 2026 matches live and in Ultra High D...
05/06/2026
The Athletic has announced that PGA TOUR highlights will be integrated into its golf coverage beginning with the Memorial Tournament presented by Workday. PGA T...
05/06/2026
When the FIFA World Cup arrives in North America in 2026, it will bring more tha...
05/06/2026
FIFA and DAZN have announced the launch of FIFA exclusively on DAZN, consolidating FIFA's content portfolio within DAZN's sports platform. The move fol...
05/06/2026
Telemundo's exclusive Spanish-language coverage of the FIFA World Cup 2026 G...
05/06/2026
Dolby Laboratories and NBCUniversal have announced that Peacock will stream Tele...
05/06/2026
Formula 1 has announced a 10-year extension to keep the Las Vegas Grand Prix on the F1 calendar through 2037. Las Vegas Grand Prix, Inc., Clark County, and the ...
05/06/2026
The broadcast-engineering team overcomes wind, speed, and salt water - and dista...
05/06/2026
Deploying both onsite and remote crews, the company is providing calibrated-came...
05/06/2026
With Inter&Co Stadium unavailable, ESPN's UFL team rebuilt its broadcast pla...
05/06/2026
One of the most exciting and informative events on the SVG annual event calendar is the Regional Sports Production Summit, an annual gathering of industry profe...
05/06/2026
For the race's third year at the historic racetrack, the broadcaster has added cameras and will incorporate multiple drones
The 158th edition of the Belmon...
05/06/2026
Ratings Roundup is a rundown of recent rating news and is derived from press rel...
05/06/2026
Built from the same recordings as flagship library
Sonuscore's LUX Orchestral Strings has been met with widespread praise since its launch in late 2025,...
05/06/2026
High-end converter, interface & headphone amp upgraded
Said to represent the next evolution of RME's all-in-one reference converter concept, the all-new...
05/06/2026
Win a Soundgas Type 636P & Type G preamps
Soundgas, one of the UK's leading vintage and boutique audio equipment specialists have just announced the lau...
05/06/2026
New leadership of Technology Systems Division at Rohde & Schwarz On July 1, 2026, Hansj rg Herrbold and Andreas H gele will take over as Executive Vice Presid...
05/06/2026
Hitachi and Intel announced a strategic collaboration to explore opportunities t...
05/06/2026
MRI-Simmons and S&P Global Mobility are expanding advanced audience capabilities...
05/06/2026
New Nielsen data shows insurance ad spend grew 11%, while consumers remain highl...
05/06/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
05/06/2026
ASG Promotes Joe Marchitto to Western Regional CTO
Brie Clayton June 5, 2026
0 Comments
Appointment to Support Engineering Alignment and Client Experi...
05/06/2026
Stargate Studios Colombia Uses DaVinci Resolve Studio for Vertical Microdramas
Brie Clayton June 5, 2026
0 Comments
End to end post in one platform al...
05/06/2026
People Need to Come First When We Use AI
Andy Marken June 5, 2026
0 Comments
It's just surviving. Life's very existence requires destruction....
05/06/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
05/06/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
05/06/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
05/06/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
05/06/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
05/06/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
05/06/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
05/06/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
05/06/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
05/06/2026
Frequency, the engine powering many of the world's leading streaming television channels, today announced the launch of In-Scene Advertising, a new monetiza...
05/06/2026
Berklee Study Reveals Video Has Become Essential to Music Careers Survey findings show social platforms have become the primary source of music for video cont...
05/06/2026
RT Radio 1 Folk Awards to take place on Tuesday 10th November 2026, Vicar Street, Dublin
Moya Brennan, D nal Lunny, Mary Black and Christy Moore among previou...
04/06/2026
Sony Electronics is introducing the SRG-AS10, a 4K 60p-compatible PTZ auto-frami...
04/06/2026
This recent grad from Spring, TX, led creative-video output for the Aggies' men's basketball team last season and has been producing video and creating ...
04/06/2026
For the first time at a women's golf major, every player in the field will r...
04/06/2026
Three Panasonic PT-RQ45 40,000-lumen 3-Chip DLP projectors made their first live...
04/06/2026
Bitmovin and Akamai have announced a collaboration with NRJ Group, a French mult...