Speech Technology Magazine


Speech Recognition Helps Preserve Seneca Language

Deep learning and speech recognition help preserve rare languages.
Posted Oct 23, 2018
Page1 of 1
Bookmark and Share

“A new research project at Rochester Institute of Technology will help ensure the endangered language of the Seneca Indian Nation will be preserved,” according to Phys.org.

RIt Researchers are using deep learning and speech recognition to “document and transcribe the traditional language of the Seneca people.” The researchers also hope to use their work to preserve other languages.

Robert Jimerson, a doctoral student at RIT, is Seneca, and he turned to friends and family to help document the language—which, according to Phys.org has fewer than 50 fluent speakers.

Since the project began in June, “the team has just over 50 hours of recorded material with people working full time on the translations that include breaking down the language into individual phonetic symbols and using this information to begin training the models.”

Page1 of 1