Skip to main content
Admissions guidance, study banks, and career tools — get started on Shalyam
Research News

Breaking Language Barriers with AI: PathSay Project

Mayur Tembhare
  1. Over 750,000 recorded sentences collected across 30 languages

  2. ,200 hours of audio collected

  3. Goal is to expand to 50 languages by the end of the year

  4. Only a few dozen languages have enough digital data for useful translation tools

Topic: Technology

Researchers at Brigham Young University are using AI to collect and preserve languages from around the world. They have already collected over 750,000 recorded sentences in 30 languages.

Thousands of languages remain invisible to modern translation technology. However, researchers and students at Brigham Young University's MATRIX lab are working to change that through a project called PathSay. They are partnering with international BYU-Pathway Worldwide students to collect speech and text data for low-resource languages.

The goal is to 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.

Researchers hope to expand the effort to 50 languages by the end of the year. They want to make it possible for anyone who speaks any language to communicate with others without knowing a common language.

Why It Matters

This project can help preserve endangered languages and cultures. It also has the potential to improve communication between people from different countries and backgrounds, which is especially important in today's globalized world.

Key Facts

  • Over 750,000 recorded sentences collected across 30 languages
  • 2,200 hours of audio collected
  • Goal is to expand to 50 languages by the end of the year
  • Only a few dozen languages have enough digital data for useful translation tools
  • Most languages are low-resource, meaning they lack sufficient translated sentences online

Key Terms

Low-resource language
A language that lacks sufficient translated sentences online to train AI models
Endangered language
A language with only a few dozen native speakers left, at risk of disappearing

Implications

This project can help preserve endangered languages and cultures. It also has the potential to improve communication between people from different countries and backgrounds, which is especially important in today's globalized world.

Source: https://phys.org/news/2026-07-pathsay-ai-language-barriers.html

Leave a comment

← All research

Get Exclusive Insights with Every Issue

Join Shalyam Newsletter

Stay ahead in education, research, and innovation—straight to your inbox.