Sony Pixel Power calrec Sony

How Deep Learning Is Aiding Preservation of Seneca and Other Endangered Languages

03/01/2019

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.
LINK: https://blogs.nvidia.com/blog/2019/01/02/deep-learning-preserves-senec...
See more stories from nvidia

Most recent headlines

05/01/2027

Worlds first 802.15.4ab-UWB chip verified by Calterah and Rohde & Schwarz to be demoed at CES 2026

Worlds first 802.15.4ab-UWB chip verified by Calterah and Rohde & Schwarz to be ...

09/10/2026

Dolby Expands Dolby OptiView Platform with New Capabilities at IBC 2026

September 10 2026, 06:00 (PDT) Dolby Expands Dolby OptiView Platform with New Capabilities at IBC 2026 New Sports Intelligence helps providers better unders...

07/10/2026

Dalet Flex LTS Delivers Smarter Media Operations from Ingest to Distribution

Dalet, a leading technology and service provider for media-rich organizations, today announced the latest Long-Term Supported (LTS) release of Dalet Flex. Build...

11/09/2026

Atomos Debuts New HDR Monitors at IBC2026

Share Copy link Facebook X Linkedin Bluesky Email...

11/09/2026

Calrec to Unveil Type RT Compact Console at IBC2026

Share Copy link Facebook X Linkedin Bluesky Email...

11/09/2026

Lightware Launches LARA 2 with New Architecture for More...

Lightware has announced the launch of LARA (Lightware Advanced Room Automation) 2.0, a major upgrade to its built-in room automation platform, introducing impro...

11/09/2026

MusiMap launches latest technology unlocking new commerci...

10 September 2026 - MusiMap, the B2B music intelligence company that is transforming how companies can harness the emotional power of music to reach consumers a...

11/09/2026

Matrox Video Integrates Matrox ORIGIN with NVIDIA Holosca...

Matrox Video today announced an integration between Matrox ORIGIN and NVIDIA Holoscan for Media, enabling Matrox ORIGIN media services to be provisioned, config...

11/09/2026

Net Insight brings cloud-native live media orchestration...

Net Insight today announced that its cloud-native live media orchestration is now available through Oracle Cloud Marketplace, providing broadcasters, production...

11/09/2026

Calrec to Unveil Type RT Compact Console at IBC 2026

Share Copy link Facebook X Linkedin Bluesky Email...

11/09/2026

Biggest functionality boost yet makes Buttons the perfect...

Version 1.8 will bring advanced routing control, new workflow tools, boosted control panel flexibility and ease of integration into IP networks...

11/09/2026

Ikegami Announces Four New UNICAM XE Series Cameras

Ikegami announces four additions its UNICAM XE range of 4K-UHD cameras with the introduction of the UHK-X700VN, UHK-X750VN, UHK-X600VN and UHK-X650VN. Developed...

11/09/2026

DHD Launches New MX3 Consoles - Modular to the Core

DHD.audio has chosen IBC2026 as the launch venue for a major new addition to its broadcast sound production platform: the MX3 console range. MX3 retains the mod...

11/09/2026

Sony To Showcase Latest Production Technology At IBC2026

Share Copy link Facebook X Linkedin Bluesky Email...

11/09/2026

EKT To Feature New Linux-Based ATSC 3.0 STB At IBC2026

Share Copy link Facebook X Linkedin Bluesky Email...

11/09/2026

Jimmy Kimmel Shifts Political Interview to YouTube Over FCC Worries

Share Copy link Facebook X Linkedin Bluesky Email...

11/09/2026

Remembering 9/11: 25 Years of TV Tech Coverage

Share Copy link Facebook X Linkedin Bluesky Email...

11/09/2026

Tiger Group To Auction Equipment from a National Broadcasting Studio

Share Copy link Facebook X Linkedin Bluesky Email...

11/09/2026

Grass Valley Launches AVORA at IBC2026

Share Copy link Facebook X Linkedin Bluesky Email...

11/09/2026

Survey: Low Latency for Live Streaming Is Industrys Top Challenge

Share Copy link Facebook X Linkedin Bluesky Email...

11/09/2026

Atomos Debuts New HDR Monitors at 2026 IBC Show

Share Copy link Facebook X Linkedin Bluesky Email...

11/09/2026

Grass Valley Launches AVORA at IBC2026 Bringing All in On...

New standalone solution gives production teams everything they need to create, produce and deliver live content from one flexible system. Grass Valley today an...

11/09/2026

Wave Central a Domo Broadcast Company Named Recipient of...

Recognition honors the development of FPV drone camera systems for live sports broadcast coverage Wave Central, a Domo Broadcast Company that develops advanced...

11/09/2026

Teradek Launches Bolt 7 A Unified Wireless System for Zer...

Teradek, the industry leader in zero-delay wireless video solutions, announced the launch of Bolt 7, which now includes a unified wireless video and data system...

11/09/2026

ACT Pixel Academy Announces Autumn Courses

The ACT Entertainment tvONE and Green Hippo Pixel Academy has released its autumn course schedule, with hands-on training dates in September, October and Novemb...

11/09/2026

Scientists discover a new way that a disease-linked protein comes apart

LA JOLLA, CA-Transthyretin amyloid disease (ATTR) is a progressive, life-threatening condition caused when the protein transthyretin (TTR) breaks apart and aggr...

11/09/2026

Major Update to Blackmagic Cloud

Major Update to Blackmagic Cloud Brie Clayton September 10, 2026 0 Comments Blackmagic Design has announced a major update to Blackmagic Cloud which a...

11/09/2026

Dalet Helps Media Organizations Navigate the Rise of Synthetic Content with NVIDIA AI

Dalet Helps Media Organizations Navigate the Rise of Synthetic Content with NVID...

11/09/2026

Benetti Menswear Tees Up for 2026 Amgen Irish Open on RT

RT has today announced Benetti Menswear as the sponsor of its 2026 Amgen Irish Open coverage for a sixth consecutive year, further strengthening the heritage c...

10/09/2026

First AI-Generated Golf Announcer To Debut During New Mexico Open

Duff Foreman is an AI-generated announcer who will add color to this month's New Mexico Open...

10/09/2026

IBC 2026: Bitmovin Rolls Out Encoder Version 3

Bitmovin is rolling out Encoder Version 3, the next major release of the technology behind its VOD and Live Encoders. Version 3 is built on a premise every stre...

10/09/2026

IBC 2026: Net Insight Highlights Open Live Media for Controlled Live Services

At IBC2026, on booth 1.B47, Net Insight will showcase Open Live Media, its architecture for delivering resilient live media services across networks, partners, ...

10/09/2026

PWHL, Scripps Sports Sign National Television Deal for 2026-27 Season

The Professional Women's Hockey League (PWHL) and Scripps Sports have announced a national broadcast rights agreement for the 2026-27 season, a landmark par...

10/09/2026

IBC 2026: Trusted Partner Network Debuts Fix It or Risk It to Tackle Everyday Security Risks

The Trusted Partner Network (TPN), the global content security initiative powere...

10/09/2026

NFL Brings Back Creator Programs to Deliver Access, Original Storytelling During the 2026 Season

The NFL is launching its most expansive creator programming yet, bringing togeth...

10/09/2026

Sportsnet Removes 150 Blackouts for More National NHL Games Than Ever in 2026-2027 Season

Sportsnet is set to deliver its biggest hockey season ever with a national sched...

10/09/2026

IBC 2026: LiveU Showcases Starlink for News and Sports Broadcast as Clarus Integrated Reseller

LiveU is now a Clarus Integrated Reseller, bringing Starlink's fast, reliabl...

10/09/2026

IBC 2026: Mimir Develops Single Layer for Content, Metadata, AI Orchestration

Mimir is the cloud-native media production platform built for teams that need to move media fast across live, archive, web, social, and broadcast workflows. At ...

10/09/2026

IBC 2026: ATSC 3.0 To Receive Technology & Engineering Emmy Award for Significant Advancement in Television Broadcasting

ATSC is being honored with a 2026 Technology & Engineering Emmy Award by the Nat...

10/09/2026

Audio-Technica Presents BP880R Contact Transducer for Immersive Sports Broadcast, Production Audio Enhancement

Audio-Technica has introduced the BP880R Contact Transducer, a specialized micro...

10/09/2026

ESPN, ION Team Up to Broadcast WTGL Starting on Nov. 8

TMRW Sports in partnership with the LPGA, today announced multiyear U.S. media rights agreements with ESPN and Scripps Sports/ION to bring WTGL, the new women&#...

10/09/2026

SportsNet Pittsburgh Honors Roberto Clemente Day With Second-Annual Live Spanish-Language Pirates Telecast

SportsNet Pittsburgh (SNP) in partnership with Major League Baseball and the Pit...

10/09/2026

Tennis Channel Gives Fans Options With Premium Subscription on Roku

Tennis Channel announced today its launch as a Premium Subscription on The Roku Channel. Tennis Channel offers viewers a single home for Tennis Channel and Ten...

10/09/2026

IBC 2026: Dolby Expands Dolby OptiView Platform With New Capabilities

Dolby has announced major updates to Dolby OptiView, its live sports platform, ahead of IBC 2026. The updates include new AI-powered intelligence to better unde...

10/09/2026

Dalet Names Brian Doheny as CEO

Dalet has appointed Brian Doheny as CEO. Doheny joined Dalet as President and Chief Revenue Officer in April 2026. Since joining Dalet, Doheny has led the compa...

10/09/2026

IBC 2026: Sony Demonstrates Various Creative Solutions for Attendees at the RAI

Sony, as well as its partner company Nevion, is starting IBC 2026 with a handful of announcements for attendees to see on the show floor. Sony Announces the 4t...

10/09/2026

SoFi Stadium Solidifies Production Output With Multi-Layered Tech Renovation

The six-year-old venue is expanding capabilities for NFL action, Super Bowl LXI, 2028 Summer Olympics SoFi Stadium, as well as the surrounding area known as Ho...

10/09/2026

Acon Digital introduce Acoustica 8

Editing, restoration & mastering suite upgraded Acon Digital Acoustica 8 audio editing restoration mastering software. Acon Digital have just launched the la...

10/09/2026

Readipop & XOX open XOX Studio

Classic synths & drum machines available to play Based in Reading, UK, Readipop are a music and arts charity with a long track record of innovative, partici...

10/09/2026

Neumann launch the KH 310 II & KH 350

Popular model updated & new addition introduced With many of the models in Neumann's KH family now boasting onboard DSP and support for the company'...