Technology content trusted in North America and globally since 1999
8,556 Reviews & Articles | 66,525 News Posts

Microsoft shows off new speech recognition technology that converts a speaker's voice into another language

New Microsoft tech showed off is capable of converting speaker's voice into another language

By: Anthony Garreffa from Nov 12, 2012 @ 6:35 CST

Rick Rashid, Microsoft's Chief Research Officer, has recently shown off a new speech recognition technology that converts a speaker's voice into a completely different language. The example used in the video below converts Rashid's English words into computer-generated Chinese language. Rashid took to a blog post, explaining:

Though it was a limited test, the effect was dramatic, and the audience came alive in response. When I spoke in English, the system automatically combined all the underlying technologies to deliver a robust speech to speech experience-my voice speaking Chinese. You can see the demo in the video above. The results are still not perfect, and there is still much work to be done, but the technology is very promising, and we hope that in a few years we will have systems that can completely break down language barriers.

Rashid also adds:

In other words, we may not have to wait until the 22nd century for a usable equivalent of Star Trek's universal translator.

Now that is some cool tech! Microsoft could really have something here for smart devices...


Related Tags