Researchers Develop a System Translating University Lectures in Multiple Languages

Tuesday, June 18, 2019 - 13:55

Researchers of Nara Institute of Science and Technology (NAIST), Japan, have developed a new machine translation system that outputs subtitles in multiple languages for archived university lectures.

According to the Science Daily report, as countries like China and Japan expand their international student cohort, this system could relax language demands and allow the students to study in their mother tongue.

"NAIST has 20% foreign students and, while the number of English classes is expanding, the options these students have are limited by their Japanese ability," explains NAIST Professor Satoshi Nakamura, who led the study.

Nakamura's research group acquired 46.5 hours of archived lecture videos from NAIST with their transcriptions and English translations, and developed a deep learning-based system to transcribe Japanese lecture speech and to translate it into English. While watching the videos, users would see subtitles in Japanese and English that matched the lecturer's speaking.

The archived footage used for the evaluation consisted of lectures from robotics, speech processing and software engineering. Interestingly, the word error rate in speech recognition correlated to disfluency in the lecturers' speech. Another factor from the different error rates was the length of time speaking without pause. The corpus used for the training was still insufficient and should be developed more for further improvements.


Popular News

Latest News