Forget Rosetta Stone — researchers at Microsoft have developed a program that uses speech recognition software to translate what someone is saying into another language using a modified version of the person’s own voice.
According to MIT’s Technology Review, the software can translate any combination of 26 different languages. Researcher Frank Soong demonstrated it at Micrsoft’s campus in Redmond, Washington by translating the voice of his boss into Spanish, Mandarin Chinese and Italian.
One of the more impressive aspects of the software is how it uses the speaker’s original voice in its translations, which it can pick up after the user spends just an hour with it. Shrikanth Narayanan, a professor at the University of Southern California, explains why that is important:To anyone who’s ever watched Star Trek, the appeal of a “universal translator” is obvious. Soong says it could help travelers communicate while traveling abroad, translate directions for GPS apps to make driving in foreign countries easier and help students who are learning new languages.
“The word is just one part of what a person is saying,” he says, and to truly convey all the information in a person’s speech, translation systems will need to be able to preserve voices and much more. “Preserving voice, preserving intonation, those things matter, and this project clearly knows that,” says Narayanan. “Our systems need to capture the expression a person is trying to convey, who they are, and how they’re saying it.”