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 ...
01/06/2026
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...
01/05/2026
January 5 2026, 18:30 (PST) NBCUniversal's Peacock to Be First Streamer to ...
01/04/2026
January 4 2026, 18:00 (PST) DOLBY AND DOUYIN EMPOWER THE NEXT GENERATON OF CREATORS WITH DOLBY VISION
Douyin Users Can Now Create And Share Videos With Stun...
20/01/2026
SVG Sit-Down: BitFire's Jim Akimchuk on the Future of Cloud, Remote, Softwar...
20/01/2026
From architecture to reality: What CBC's Milano Cortina 2026 workflows tell ...
20/01/2026
Milano Cortina 2026: Making the Winter Olympics and Paralympics workflow work fo...
20/01/2026
Countdown to Milano Cortina 2026: SVG Launches SportsTechLive Blog in Lead-up to...
20/01/2026
Grand finale: Rally Saudi Arabia pushes WRC to make the most of cameras and dron...
20/01/2026
State of Change: What's Happening in the Remote-Production Business?NEP Group, Game Creek Video, Dome Productions, Mobile TV Group, Program Productions exec...
20/01/2026
CFP National Championship 2026: A Look Back at SVG's Complete CoverageGo behind the scenes with ESPN, Game Creek Video, Van Wagner, and the champion Indiana...
20/01/2026
The Gotham, Film Independent, and Creators Coalition on AI Join Alliance
by Michelle Satter, Founding Senior Director, Sundance Institute's Artist Programs...
20/01/2026
The National Film and Video Foundation (NFVF), an agency of the Department of Sp...
20/01/2026
December, the first month of winter and the holiday season, has traditionally encouraged families to spend time together in front of the television. During this...
20/01/2026
During December, streaming's share of TV viewing in Mexico settled at 24.3%, an increase of 0.1 share points from the previous month.
Disclaimer: YUMI TV,...
20/01/2026
Christmas Day is Most-Streamed Day Ever with 55 Billion Viewing Minutes, led by...
20/01/2026
Share Share by:
Copy link
Facebook
X
Whatsapp
Pinterest
Flipboard...
20/01/2026
Disguise and ASB GlassFloor today announced a strategic partnership that turns the arena floor into a fully customizable interactive digital surface. This will ...
20/01/2026
Last summer, ITV celebrated the tenth anniversary of its popular reality dating show, Love Island. To ramp up the excitement of series 12 (launched in the UK on...
20/01/2026
Berklee's Mark Ethier Named One of SPIN's Most Influential People in Mus...
20/01/2026
Share Share by:
Copy link
Facebook
X
Whatsapp
Pinterest
Flipboard...
20/01/2026
Share Share by:
Copy link
Facebook
X
Whatsapp
Pinterest
Flipboard...
20/01/2026
Emergent, a provider of AI-powered media production solutions, today announced its presence at ISE 2026 in Barcelona, taking place February 3 6, where it will u...
20/01/2026
Back to All News
Netflix and Warner Bros. Discovery Amend Agreement to All-Cash Transaction
Business
20 January 2026
Global
Link copied to clipboard
All-C...
20/01/2026
Back to All News
Now You Can Play a Role in Our Live Events With Real-Time Voting
Elmar Nubbemeyer
VP, Member Product
Product
20 January 2026
Global
Link...
19/01/2026
CFP National Championship 2026: Indiana Football's Digital Crew Generate Hyp...
19/01/2026
CFP National Championship 2026: Van Wagner Relies on Experience for Indiana-Miam...
19/01/2026
CFP National Championship 2026: Game Creek Video Fields Premiere IP Compound for...
19/01/2026
CFP National Championship 2026: For a Slew of Studio Shows, ESPN Turns Hard Rock...
19/01/2026
CFP National Championship 2026: ESPN's Sweeping Live Game Production Leverag...
19/01/2026
The new L3Harris NOVA binocular system is the every-soldier goggle' - and the beginning of a new era for night-vison capability....
19/01/2026
The Majority of Those Surveyed Prefer to Buy Brands Who Advertise in Content Tha...
19/01/2026
Back to All News
Straight to Hell' Sets April 27 Premiere: Teaser Trailer,...
19/01/2026
New Workflow Enhancements for All Broadcast Pix Systems, Plus 4-Channel ISO Recording for Hybrid and Roadie Tyngsboro, Mass. - January 2025 - Broadcast Pix ann...
19/01/2026
Monday 19 January 2026
Sky News reinvents News at Ten for the modern audience with The Wrap
Sky News today announces The Wrap, a bold evolution of its 10pm ou...
19/01/2026
Back to All News
Netflix Announces the Series Nights & Days, Directed by Kamila...
19/01/2026
DPA Microphones is striking a new chord in piano miking with the debut of its DPK2015 Piano Stereo Kit, an out-of-the-box, plug-and-play miking solution that ta...
19/01/2026
DPA Microphones will present its 4099 CORE Instrument Microphone and redesigned...
19/01/2026
Trianel relies on Arvato Systems for future-proof data center operations
Moving to the cloud: Arvato Systems implements extensive IT migration project
Migrat...
19/01/2026
Celebrating 21 Years of the RT Choice Music Prize
RT Choice Music Prize
In association with IMRO and IRMA
Irish Album of the Year 2025 - Shortlist Announce...
18/01/2026
January 18 2026, 21:30 (PST) Dolby Cinema Arrives in Bengaluru: Dolby Laborator...
17/01/2026
Lightware, an industry leader in signal management, is helping to elevate the Google Meet experience with the introduction of an integration with Taurus UCX. Th...
17/01/2026
Clear-Com announced a strategic partnership with NETGEAR AV to offer four high-performance networking switches as original equipment manufacturer (OEM) solutio...
17/01/2026
QuickLink, a leading provider of award-winning video production and remote guest contribution solutions, today announced a new U.S. distribution partnership wit...
17/01/2026
NUGEN Audio announces the latest evolution of MasterCheck, its industry-trusted optimization plug-in for cross-platform mastering and loudness verification. Des...
17/01/2026
BHV has announced that it will highlight its new SportsBox remote vision mixer and picture processor at ISE in Booth #4H900 marking its official introduction in...
17/01/2026
Clear-Com will return to ISE 2026 to demonstrate its latest intercom solutions for broadcast, live production, and AV professionals. Exhibiting at Stand #4P700...
17/01/2026
Grass Valley, a leading provider in live production solutions, will exhibit at ISE 2026 in Barcelona from February 3 6, presenting its vision for how modern Bro...
17/01/2026
Utelogy Corporation, the global leader in connected workplace management, monitoring, control, automation and analytics closes out a record-breaking 2025. The c...
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.
