Thousands of the world's languages remain largely invisible to modern translation technology, but researchers and students at Brigham Young University are working to change that. Through a project called Pathsay, students in the BYU MATRIX lab are partnering with international BYU-Pathway Worldwide students to collect speech and text data for low-resource languages, helping preserve linguistic heritage and improve access to translation tools for communities often overlooked by mainstream technology.
The project has already collected more than 750,000 recorded sentences and 2,200 hours of audio across 30 languages, including Afrikaans, Bislama, Chichewa, Cusco Quechua, Dholuo, Efik, Fante and Fon, among others. Researchers hope to expand the effort to 50 languages by the end of the year.
Fewer than 50 of the world's roughly 7,000 languages have enough digital data available to create truly useful translation tools. Only the top dozen languages—languages such as English, Portuguese, Italian, Korean and Chinese—are considered "high-resource."
"Any language beyond the top 100 is what we would call low-resource," BYU computer science professor Steve Richardson said. "There are not enough translated sentences online to train models like Google Translate to handle those languages. Then, the other half of the world's languages aren't even written, and you find what we call endangered languages—languages that may just disappear with a few dozen native speakers left. For those kinds of languages, the goal is to preserve the culture and the heritage—to not lose the valuable knowledge of those people."
Many languages overlooked by mainstream technology are actively spoken by hundreds of thousands or even millions of people.
BYU-Pathway Worldwide students from countries such as South Africa, Nigeria and Kenya record sentences in their native language through a program developed by students in the lab.
"I get to preserve my own language," BYU-Pathway student Thomas from Ghana said in a Y Magazine podcast interview. "People do not really get to speak their local languages even to their colleagues, and so getting a chance to learn ... about your local language has been a really incredible thing to me."
In addition to preserving heritage, the MATRIX lab is driven by the desire to provide translation resources for these communities.
"My vision is to enable anyone who reads, speaks or signs any language in the world to communicate with anyone else who reads, speaks or signs another language without knowing a common language," Richardson said. "For example, somebody who signs Libras in Brazil communicating with somebody who speaks Zulu in South Africa."
For Richardson and his students, the ultimate goal is to make the gospel of Jesus Christ available to all. According to the BYU-Pathway students, recording gospel resources in their own languages has had a significant spiritual impact.
"We as Christians talk about spreading the gospel to the world so that everyone can hear it in their own tongue," Richardson said. "But how are we going to reach the billions of people that speak these low-resource languages? How are they going to receive the gospel if we don't figure out how to translate into these low-resource languages?"
With this spiritual mission in mind, students in the MATRIX lab are using the collected data to create AI models that can recognize, translate and generate the low-resource languages of the world.
"Members across the world deserve to learn of Christ in their own native language," lead research assistant Ammon Shurtz said in a BYU Philanthropies article. "That motivates me ... so that they—and millions of others—can have access to these tools and opportunities."
Who's behind this story?
BA art history, MA material culture. Former museum editor, paramedic, and transplant coordinator. Editing for Science X since 2021. Full profile →
Master's in physics with research experience. Long-time science news enthusiast. Plays key role in Science X's editorial success. Full profile →
Citation: PathSay Project uses AI to cross language barriers (2026, July 16) retrieved 17 July 2026 from https://phys.org/news/2026-07-pathsay-ai-language-barriers.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.