ETRI Releases Multilingual Speech Recognition with 24 Languages

Korea's Electronics and Telecommunications Research Institute (ETRI) has developed a multilingual speech recognition technology that understands 24 languages, including Korean, English, Chinese, Japanese, German, French, Spanish, Russian, and several south Asian languages. The company plans to expand that to 30 languages this year.

The technology uses self-supervised and supervised learning models and audio data generation using text-to-speech.

"This technology expects to be of great help in enhancing the global competitiveness of Korea's artificial intelligence field and securing technological sovereignty," said Kim Sang-hun, project leader, in a statement.