
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
09/11/2025
Dalet today announced a transformative leap forward for media operations: Agentic Artificial Intelligence (AI) that unifies the Dalet ecosystem under one natura...
06/10/2025
France T l visions, France's leading broadcaster, has received the 2025 EBU ...
17/09/2025
Tech Focus: Audio Training, Part 2 - Manufacturers Offer Extensive Online Learni...
17/09/2025
Tech Focus: Audio Training, Part 1 - A1 Shortage Remains a Major-League Challeng...
17/09/2025
It was the ultimate convergence of pop culture and literary prestige: Last night, Dua Lipa brought her Service95 Book Club podcast to the stage for a special li...
17/09/2025
During August, streaming's share of TV viewing in Mexico showed an increase of 0.4% compared to the previous month, accounting for 25% of TV viewing.
Discl...
17/09/2025
CYPRESS, Calif. FOR-A America has named Jo Aun as senior manager of product engineering, a new role responsible for guiding the planning, development and rollou...
17/09/2025
PlayBox Neo, in partnership with CIS Group, a leading provider of media and broadcast technology solutions, has successfully deployed PlayBox Neo's Dual Cha...
17/09/2025
In a relationship that mirrors societal advances in sustainability, Brightline Lighting and the Federal Energy Regulatory Commission (FERC) Headquarters have en...
17/09/2025
Clear-Com is proud to support the world-class productions of Alley Theatre, one of the oldest and largest nonprofit resident theatres in the United States. With...
17/09/2025
Arch Platform Technologies (www.archpt.io), a pioneer in automated, scalable cloud infrastructure for high-performance workflows, today announced a Strategic Co...
17/09/2025
Over 300 selected decision-makers from start-ups, corporates, and VC funds worldwide will gather for the third edition of the event, united by a single goal: to...
17/09/2025
Telestream, a global leader in media workflow technologies, is excited to announce that its flagship Vantage platform and its next-generation AI capabilities re...
17/09/2025
Mediagenix, a global leader in smart content solutions that profitably connect the right content to the right audience, proudly announces its three Best of Show...
17/09/2025
In a move to further establish a firm foothold across South East Asia, PlayBox Neo, the well-respected name in broadcast playout and channel branding, has appoi...
17/09/2025
Wisycom, a global leader in advanced wireless audio solutions, announced two major wireless solutions at IBC 2025 (Stand 8.D30). This includes the Portable RF-o...
17/09/2025
Six Berklee Alumni Win Emmy Awards The recipients were recognized for their contributions to acclaimed programs Severance, The Studio, The Penguin, SNL50: The...
17/09/2025
Applications Open for Berklee in Santo Domingo The weeklong contemporary music program will run January 5-10, 2026.
By
Colette Greenstein
September 17, 2025
...
17/09/2025
Ukrainian Students Find Creative Consonance' at Berklee Valencia Through ELIA's UAx Platform, six students from Kyiv joined Berklee Valencia for a week...
17/09/2025
Earlier this year Avid announced Kenna Hilburn as its new senior vice president of product. Recently Hilburn was promoted to Avids new Chief Product Officer, su...
17/09/2025
Transatlantic collaboration combines experience and agility to drive innovation in network design and delivery
Luxembourg, September 16, 2025 - SES, a leading ...
17/09/2025
NEW YORK Madhive has announced that the Fox Television Stations have joined its Live Sports Marketplace....
17/09/2025
SYRACUSE, N.Y. Sony Electronics has announced that it is partnering with the Newhouse School at Syracuse University to provide state-of-the-art equipment, hands...
17/09/2025
SAN JOSE, Calif. Roku has announced that the first smart projector using its Roku TV operating system, the Aurzen Roku TV Smart Projector D1R Cube, is now avail...
17/09/2025
Wednesday 17 September 2025
UK artists capture icons of stage and screen, inclu...
17/09/2025
Jo Returns to FOR-A as Senior Manager of Product Management and Engineering...
17/09/2025
For the Moon Safari anniversary tour, AIR opened the doors to their backstage. Just a few hours before the Paris concert, DPA met with two key figures of the te...
17/09/2025
Auditions will be held in Dublin, Cork and Galway
The County Parade returns f...
16/09/2025
SVG All-Stars: Leigh Michaud, Manager, Remote Operations, ESPNThe UConn grad rose from ESPN's mailroom to become one of its most valuable ops leadersBy Bran...
16/09/2025
Live From IBC 2025: Friday's Latest From Halls 1-4, Outdoor Exhibits in Amst...
16/09/2025
Live From IBC 2025: Saturday's Latest From Halls 5-7 in Amsterdam By SVG Staff
Friday, September 12, 2025 - 17:00
Print This Story
The SVG Europe and ...
16/09/2025
Live From IBC 2025: Sunday's Latest From Halls 8-10 in Amsterdam By SVG Staff
Saturday, September 13, 2025 - 17:00
Print This Story
The SVG Europe and...
16/09/2025
Live From IBC 2025: Monday's Latest From Halls 11-14 in Amsterdam By SVG Staff
Sunday, September 14, 2025 - 17:00
Print This Story
The SVG Europe and ...
16/09/2025
Amazon Prime Video Picks Up Four Hours of Early-Round Masters Coverage in 2026 By Jason Dachman, Editorial Director, U.S.
Tuesday, September 16, 2025 - 10:15...
16/09/2025
VERSANT Inks Deal for League One Volleyball as Women's Sports Rights Slate G...
16/09/2025
ESPN VP, Corporate Communications, Katina Arnold Named SVP, Disney Advertising C...
16/09/2025
IBC 2025 in Review: SVG Europe's Full Collection of Video Interviews From th...
16/09/2025
Hace una d cada, la m sica latina representaba apenas el 8% de las reproducciones globales en Spotify. Hoy, constituye m s de una cuarta parte (27%) de toda la ...
16/09/2025
A decade ago, Latin music made up just 8% of global Spotify streams. Today, it a...
16/09/2025
Spotify is expanding our video lineup with a new partnership with Zoo 55, part of ITV Studios. For the first time, acclaimed content from ITV Studios is landing...
16/09/2025
At DSEI 2025, James Dunne of L3Harris Maritime UK chaired a panel on aligning the supply chain to the warfighter, where leaders discussed modernising support fo...
16/09/2025
Calrec has strengthened its collaboration with audio metering expert RTW by integrating RTW's new TMxCore metering platform across its full range of Argo IP...
16/09/2025
College Football Scores Top Telecast in August with 16M+ Viewers on FOX, Followe...
16/09/2025
Collaboration marks the first SSP integration of Gracenote IDs, enabling show-le...
16/09/2025
AMSTERDAM The organizers of IBC2025 are reporting that 43,858 visitors from more than 170 countries attended the event, which had more than 1,300 exhibitors and...
16/09/2025
Wooden Camera announces the release of its new Accessory Collection for the FUJIFILM GFX ETERNA 55. The highlights of this collection include vital power soluti...
16/09/2025
Anton/Bauer, a leading manufacturer of mobile power solutions for broadcast and cinematic equipment, has announced the launch of Anton/Bauer Fleet Management, a...
16/09/2025
Teradek, a leading provider of video transmission and live production solutions, today announced the launch of Prism Jetpack, a groundbreaking 5G video contribu...
16/09/2025
Astera, the leader in wireless LED lighting solutions, announces the ultra-versatile SolaBulb. Building on the success of the Astera bulb family, SolaBulb intro...
16/09/2025
As the world gathered at TED2025 to explore the provocative theme "Humanity Reimagined", Clear-Com , supported by NETGEAR networking infrastructure, delivered f...