Attempts at creating a “universal translator” are getting ever-closer to the science fiction that inspired them, as Microsoft’s latest translation demonstration makes clear. Earlier this month, the tech giant took the opportunity provided by TechFest 2012 to show off its newest invention: translation software that lets you “speak” any one of 26 different languages, all in your own voice.
Although it goes by the unassuming name of Monolingual TTS, there’s nothing unassuming about its capabilities. After about an hour of “training,” the software learns your voice. Once that’s done, it can translate anything you say into one of the 26 languages it knows, using a digitally animated version of your own head and a digitally simulated version of your voice. The result is about two parts awesome, one part creepy, as you can see in the video demonstration below:
Still, it’s undeniably useful. For example, if you’re travelling and you need to communicate with someone in another country, all you have to do is speak what you want to say, and the software will repeat it for you in the correct language.
In an article on TechnologyReview.com, Microsoft researcher Frank Soong said that other applications could include translating GPS directions and helping language learners work on their pronunciation.
Why read back the translations in your own voice? University of Southern California professor Shrikant Narayanan told Technology Review that words are just one part of how we communicate through speech:
“The word is just one part of what a person is saying. Preserving voice, preserving intonation, those things matter, and this project clearly knows that. Our systems need to capture the expression a person is trying to convey, who they are, and how they’re saying it.”
Of course, this system doesn’t do that entirely. It can capture someone’s pitch and intonation fairly well, with just a slight digital edge. But it doesn’t seem like it would be able to capture the emotions behind the words, yet. The truth is, there’s usually more to translating than meets the ear, so to speak. Machine translation can be helpful if there’s no other way to communicate, but the best way to preserve the meaning that you’re trying to get across is still to use a human translator who is familiar with both cultures.