
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...
15/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
15/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
15/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
15/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
15/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
15/05/2026
Delivering a live, arena-scale production of a massively popular band is no small feat. Between expansive in-arena LED walls and a global live stream fed to onl...
15/05/2026
Connection is the heartbeat of any strong community, and with live streaming becoming more accessible in the modern era, it's much easier for faith-based or...
15/05/2026
Powered by GX 3 media servers, optimised IP-VFC workflows and on-site engineering expertise, the production delivers high-performance visuals for one of the wor...
14/05/2026
Sweetwater and Airstream have announced a custom-built Dolby Atmos mobile recording studio inside an Airstream trailer, set to tour music festivals, schools, tr...
14/05/2026
The American Association of Professional Baseball (AAPB) has announced a new par...
14/05/2026
ESPN has announced plans to transform Santa Monica Beach into a broadcast hub du...
14/05/2026
Amagi has announced a significant update to Amagi CLOUDPORT, its cloud-based broadcast playout platform. The update includes 250-plus features shipped in FY25-2...
14/05/2026
Clear-Com will exhibit at InfoComm 2026 (Booth N7005, June 17-19, Las Vegas Convention Center), introducing a new product that builds on Arcadia Central Station...
14/05/2026
Ikegami will exhibit at BroadcastAsia 2026 (Stand 5D3-1, Singapore Expo, May 20-22), introducing two new viewfinders alongside its existing camera, control, and...
14/05/2026
Grass Valley has announced that dB Broadcast has delivered new IP-based outside ...
14/05/2026
NAGRAVISION, a Kudelski Group company, has announced a partnership with the World Professional Billiards and Snooker Association (WPBSA) to launch Play Snooker,...
14/05/2026
Belden Inc. has announced a definitive agreement to acquire RUCKUS Networks from Vistance Networks for approximately $1.85 billion. The transaction has been app...
14/05/2026
NVIDIA has released the Content Localization Blueprint, a modular reference arch...
14/05/2026
Disney has announced that Disney will be the exclusive U.S. streaming home of the Banana Bowl, the Banana Ball league season championship, streaming live this ...
14/05/2026
Arkona technologies and technology partner manifold will demonstrate their production solutions on the Magna Systems and Engineering stand (Booth 5D1-1) at Broa...
14/05/2026
Haivision will host a webinar on Thursday, May 21 at 10 a.m. ET / 4 p.m. CET cov...
14/05/2026
The CW Network and ESPN have announced a sublicense broadcast agreement for The CW to televise ACC football and men's and women's college basketball gam...
14/05/2026
The agreement marks Scripps Sports' first NBA local rights deal...
14/05/2026
A new report from education-technology company Wiingy testing post-ChatGPT predictions against three years of real-world data has identified broadcasting as one...
14/05/2026
Global Citizen and FIFA have announced that Madonna, Shakira, and BTS will headl...
14/05/2026
LOS ANGELES, CA, May 14, 2026 - The nonprofit Sundance Institute announced today the cohort selected for the 2026 Episodic Lab program, taking place at Dunaway ...
14/05/2026
At Spotify, we're focused on making every listening experience feel intentio...
14/05/2026
Spotify recently welcomed songwriters, artists, executives, and music students t...
14/05/2026
New articulations, ostinatos, Motion Scoring Articulation Sets & more
Sonuscore's flagship cinematic string library has just been treated to a significa...
14/05/2026
World-class studio opens on T rkiye's Aegean coast
P r Recording & Residence have announced their official opening, introducing a new world-class reside...
14/05/2026
Now supports channel layouts up to 9.1.6
Nugen Audio have just released an update for their AI-powered dialogue intelligibility and compliance tool. Set to ...
14/05/2026
New recordings & one-key chord tool
UVI have just announced the release of Orchestral Suite 2, a ground-up redesign of their all-in-one symphonic orchestra ...
14/05/2026
Two new arrivals & expanded factory content
Rob Papen's all-encompassing plug-in and virtual instrument collection has just been treated to another upda...
14/05/2026
Embed QR codes into DAW sessions
FSK Audio's latest plug-in doesn't process audio, but serves as an organisational tool that allows QR codes to be e...
14/05/2026
SBS Board appoints Jane Palfreyman Managing Director
13 May, 2026
Media releases
The Special Broadcasting Service (SBS) Board of Directors is pleased to an...
14/05/2026
Transforming bold ideas into market-ready productions: Digital Originals returns
14 May, 2026
Media releases
SBS, NITV and Screen Australia have announced ...
14/05/2026
Australia Uncovered Returns to SBS with Bold New Season Featuring John Safran on...
14/05/2026
Rohde & Schwarz transforms spectrum complexity into situational awareness and ef...
14/05/2026
Rohde & Schwarz and Quantum Systems join forces to redefine EW and C-UAS-enabled...
14/05/2026
Rohde & Schwarz showcases STANAG aligned ARDRONIS Counter UAS capability at NATO...
14/05/2026
Code of Silence has won the BAFTA for Best Drama Series at Sunday night's ceremony at the Royal Festival Hall.
The series, starring Rose Ayling-Ellis and w...
14/05/2026
Soldiers equipped with Falcon IV radios will soon gain a sense-and-protect capa...
14/05/2026
Artists concept of the L3Harris Next Gen RTG in flight configuration, designed to provide 250 watts of reliable power for decades-long missions in deep space....
14/05/2026
Vivid Broadcast was embracing remote production long before it became the industry norm. Now, with Calrec's True Control 2.0-enabled Argo M and Type R conso...
14/05/2026
Car ad spend rises sharply in March as more auto buyers turn to electric, hybrid...
14/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...