
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...
11/08/2026
LiveUs LU900Q intelligent production unit played a central role in the host broadcast operation for the Games in Glasgow (July 23 to August 2, 2026). The host b...
11/08/2026
Jigsaw24 has appointed James Morse as Client Director, Media Sales, as it deepens its focus on sports, live events and integrated production. His appointment co...
11/08/2026
Net Insight today announced that DMC Production Norway has selected its Open Live Media solution to centralize the production of Blinkfestivalen 2026. Combining...
11/08/2026
Modular HEVC and JPEG XS workflows enabled resilient, ultra-low-latency delivery for leading linear and digital media platforms across all 104 matches
Appear A...
11/08/2026
Homecoming Artist Spotlight: Fabiola M ndez The first cuatrista to graduate from Berklee talks about the community that shaped her career ahead of her Homecom...
11/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
11/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
11/08/2026
Dalet, a leading technology and service provider for media-rich organizations, today announced Dalet Solution Suites, a new portfolio of cloud-native solutions ...
11/08/2026
Mediagenix, a global leader in smart content solutions to profitably connect the right content to the right audience, will showcase how media companies can prep...
11/08/2026
Transforming your audience into advocates with Kelsey Gamble 10 August 2026
Building community, harnessing fandom for marketing and activating the four stages ...
11/08/2026
A Day in May airs Wednesday 12 August at 9.35pm RT One and RT Player
A Day in May revisits the people and stories behind Ireland's historic marriage equa...
11/08/2026
As AI shifts from chatbots to autonomous agents, open models are serving market ...
11/08/2026
The open source ecosystem is making it easier for AI enthusiasts and developers to build, customize and run increasingly capable agents locally.
Throughout Au...
10/08/2026
Weekly immersive broadcasts will feature 8K 3D video, a 180-degree field of view...
10/08/2026
Saturation plug-in free until 20 August 2026
fedDSP have announced the launch of Raiju, a new guitar pedal-style saturation plug-in that's capable of de...
10/08/2026
New mix-comparison & feedback tool
Independent Swedish record label I/O Music have recently released a handy new tool that provides artists, engineers, prod...
10/08/2026
Additive soft synth gains free counterpart
Sound Radix have just released a free monophonic additive software synth that's based on the same engine as t...
10/08/2026
Chroma integrates MXO oscilloscopes into ATS 8000 platform, rounding out its hig...
10/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
10/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
10/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
10/08/2026
Students in the Technology and Applied Composition (TAC) program at the San Francisco Conservatory of Music (SFCM) gain rare, real world experience in professio...
10/08/2026
FOR-A is using its presence at IBC2026 (stand 2.B53, Amsterdam RAI, 11 14 September) to show how its products deliver the answers to the real challenges faced...
10/08/2026
Frontier EU, official Peplink distributor for Europe, will exhibit at IBC 2026 in Amsterdam from 11 to 14 September, presenting live demonstrations of how Pepli...
10/08/2026
Remote Editing Without Cloud Storage Premiere Pro
Michael Cioni August 10, 2026
0 Comments
This is a step-by-step guide that demonstrates how to setup...
10/08/2026
Stunning Pixelated ASCII Effect for Apple Motion
Simon Ubsdell August 10, 2026
0 Comments
Apple Motion is perfect for building this popular ASCII unic...
10/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
10/08/2026
Monday 10 August 2026
Welcome to the Show : Sky Creative unites football fans w...
10/08/2026
Red Seat Ventures' Speakeasy Brings Video to Apple Podcasts, Beginning with ...
10/08/2026
A major unconventional operator increased monthly pumping hours by more than 30% by automating critical frac completion processes and eliminating common sources...
10/08/2026
Today, Apple and Major League Baseball (MLB) unveiled the September schedule for...
09/08/2026
Combines physical modelling with subtractive synthesis
reFX, the company behind the popular Nexus and Vanguard2 soft synths have announced the launch of the...
09/08/2026
Human nuance is not a switch
Dreamtonics have built up a solid reputation off the back of their Synthesizer V Studio software, a powerful vocal-synthesis t...
09/08/2026
COW Jobs: Documentary Editor - Remote
Brie Clayton August 9, 2026
0 Comments
Documentary Editor
July 31, 2026COW Jobs: Lead Generation Representativ...
08/08/2026
Enhanced ToneNET integration & 220 new Premium V2 Tone Models
IK Multimedia have just launched a public beta of Tonex 2.0, a release which is said to repres...
08/08/2026
Honouring the drum machine that redefined modern music
Roland have announced their plans for this year's 808 Day, a day that was founded to celebrate th...
08/08/2026
The National Film and Video Foundation (NFVF), an agency of the Department of Sp...
08/08/2026
Star Wars Hyperspeed Tutorial: The No-Echo Method in After Effects
Graham Quince August 8, 2026
0 Comments
The Echo Effect to create long streaks is n...
08/08/2026
Chyron Releases AXIS 4.0 With Expanded News Workflows and Richer Map Storytellin...
08/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
08/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
08/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
08/08/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
08/08/2026
Foundry Unlocks Professional-Grade AI for VFX with Griptape Enterprise; Appoints...
08/08/2026
Award Winning New Horror Film Shot Using Blackmagic Camera App
Brie Clayton August 7, 2026
0 Comments
Fire Alive, shot using the Blackmagic Camera i...
08/08/2026
The global buildout of AI infrastructure reached a new milestone today - Firebird, an emerging AI cloud, launched the CIS region's largest AI factory in Arm...
07/08/2026
Diversified has appointed industry veteran Pete Emminger as global chief technology officer. Emminger will lead the company's global go-to-market technology...