Microsoft’s Speech Translator Uses Speakers Own Voice

Microsoft is developing a language translator that able to translate not only text but also the speakers own voice. Rick Rashid, Microsoft’s chief research officer, demonstrated the system at a presentation in Tianjin, China. Accordind to Rick it uses a technique called “deep neural networks,” which is a way of connecting computers so that they work more like a human brain. During the presentation, he demonstrated the machine and when his own voice repeated a phrase in Chinese, even though he personally can’t speak Chinese.

But it’s not flawless, as Rick’s talk revealed. At one point, the text on the screen behind him said “about one air out of every four or five words,” when the word he wanted was “error.” About a minute and a half later, the text said, “Take the text that comes from my voice, input dot iii translation system. It really happen to stop.” for “It takes the text that comes from my voice and puts it into the translation system. It really happens in two steps.”

They hope to develop this new method further more and breakdown language barrier between people.