
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...
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...
02/05/2026
Dalet, a leading technology and service provider for media-rich organizations, t...
01/05/2026
January 5 2026, 18:30 (PST) NBCUniversal's Peacock to Be First Streamer to ...
14/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
14/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
14/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
14/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
14/04/2026
Shotoku Introduces the World to Aura P2 PTZ Prompter Panner at NAB 2026
New system removes PTZ pan restrictions for teleprompter-based productions
Shotoku US...
14/04/2026
Integration of Vantage, Pulse, and Telestream UP with Grass Valley AMPP Ecosystem enables scalable, interoperable workflows spanning live production and file-ba...
14/04/2026
Enterprise growth leader to scale Dalet's next phase of innovation and global expansion
New York, NY April 14, 2026 Dalet, a leading technology and ser...
14/04/2026
Berklee Celebrates Prince's Legacy in Two-Night Signature Series Event Directed by Tia Fuller, the Prince Project (April 16-17) brings together more than ...
14/04/2026
Arooj Aftab Is Anything but Predictable The singular artist explores the juxtaposition of grief and joy, dark and light, in her distinctive sound.
April 14, ...
14/04/2026
Appear launches include XM estate management and new X Platform processing enhancements to add density for next-generation hybrid & IP workflows, X5 is also now...
14/04/2026
Addressing the needs of a new generation's viewing habits, Synamedia launches GO Shorts. The AI-powered module turns existing catalogues into TikTok-style ...
14/04/2026
Vubiquity, an Amdocs company and global leader in technology-led media services, will be showcasing a new end-to-end streaming solution in collaboration with El...
14/04/2026
LiveU today announced a significant expansion of its collaboration with Sony Corporation, introducing integrated support for Sony's file-based workflow solu...
14/04/2026
Open Broadcast Systems (https://www.obe.tv/) has announced that BBC World Service has selected its decoders for IP Television distribution. The high-quality, lo...
14/04/2026
Blackmagic Design Announces DaVinci Resolve 21
Brie Clayton April 14, 2026
0 Comments
Major update adds new Photo page bringing Hollywood's most a...
14/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
14/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
14/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
14/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
14/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
14/04/2026
Wowza will return to NAB Show 2026 with a set of live demonstrations focused on how video infrastructure is evolving for a new generation of AI-powered and oper...
14/04/2026
Stegawave Debuts Real-Time Forensic Watermarking to Tackle Piracy in Live Sports...
14/04/2026
Living in Boston: A Guide for Incoming Boston Conservatory Students From navigating the T to balancing school with professional gigs, a current student shar...
14/04/2026
Just What Is Genre These Days, Anyway? Understanding the business and art of genre-bending in 2026.
April 13, 2026
By
Bryan Parys
Illustration by Jack Fla...
14/04/2026
Lenora Helm Hammonds Is Turning Passion Into Plan A The dean of the Professional Education Division has seen the industry from all sides. Now shes bringing it...
14/04/2026
How Michelle Zalabak Found Her Dream Career in Music and Finance The Warner Music Group deal analysis manager helps determine what artist catalogs are worth a...
14/04/2026
Luxembourg, April 14, 2026 - SES, a leading space solutions company, today annou...
13/04/2026
ToolsOnAir Composition Builder 2026 Boilerplate
More Details: The Composition Builder 2026 application for macOS enables TV stations and Live Event broadcast...
13/04/2026
ToolsOnAr just:live pro 2026 Boilerplate
More Details: just:live pro 2026 is a Multi-Channel Live Production Playout solution for video and static or real-ti...
13/04/2026
ToolsOnAr just:play pro 2026 Boilerplate
More Details: just:play pro 2026 is a Multi-Channel automated 24/7 Master Control playout solution with SD, HD and U...
13/04/2026
ToolsOnAr live:cut 2026 Boilerplate
More Details: live:cut is an option to just:in mac pro 2025 and enables multicamera production workflows for up to 16 cam...
13/04/2026
ToolsOnAir Just In Mac Lite NDI 2026 Boilerplate
More Details: The Just In Mac Lite NDI application is a streamlined media capture solution designed specific...
13/04/2026
ToolsOnAir Just In Mac Lite 2026 Boilerplate
More Details: The Just In Mac Lite application is a streamlined media capture solution designed specifically for...
13/04/2026
ToolsOnAir just:in mac pro 2026 Boilerplate
More Details: just:in mac pro is a macOS-based client-server multichannel capture solution to record SDI, HDMI, N...
13/04/2026
Telos Alliance has announced that J nger Audio has joined the EBU ADM Implementers Group (ADM-IG) as a founding member. The group is focused on advancing ADM an...
13/04/2026
Grass Valley will demonstrate its Alliance Partner ecosystem at NAB Show 2026 (Booth C2408, Central Hall, April 19-22), showing AMPP integrations across live pr...
13/04/2026
Media Links will exhibit at NAB Show 2026 (Booth W2033), demonstrating IP transport solutions for live production including hitless protection technology, Xscen...
13/04/2026
NBC Sports has announced a programming, distribution, and sales partnership with...
13/04/2026
FloSports has promoted Chief Operating Officer Jayar Donlan to President, effective immediately. In his new role, Donlan will lead the company's commercial,...
13/04/2026
PanCam Pictures, the documentary production company founded by Paul Camarata, us...
13/04/2026
Mimir will exhibit at NAB Show 2026 (North Hall, Booth N2850), demonstrating its cloud-native media production platform with new capabilities including Mimir Cu...
13/04/2026
BBright has announced that its IP Gateway now supports the Reliable Internet Stream Transport (RIST) protocol. The addition will be introduced at NAB Show 2026 ...
13/04/2026
Net Insight has been awarded a development project through the European Space Agency's Navigation Innovation and Support Program (NAVISP), with co-funding f...
13/04/2026
intoPIX will exhibit at NAB Show 2026, marking the company's 20th anniversary. The company will demonstrate its JPEG XS compression portfolio and IPMX-appro...