Google has confirmed that it is working on a technology to allow real-time language translation on the phone.
The software would integrate voice recognition and the company’s Google Translate facility.
The company reckons it could have a working product within two years – so there’s no need to fork out for those Mandarin lessons any longer.
“Clearly, for it to work smoothly, you need a combination of high-accuracy machine translation and high-accuracy voice recognition, and that’s what we’re working on,” Franz Och, Google’s head of translation services, told The Times.
“If you look at the progress in machine translation and corresponding advances in voice recognition, there has been huge progress recently.”
Google Translate already handles 52 languages, and Google will be able to take advantage of its massive archive of translated material to continually improve accuracy. And because phones are generally used by only one person, voice recognition software would be able to adapt to the user’s accent and intonation.
Various companies and academics have been working for years to develop something like this. Carnegie-Mellon University has been beavering away for three years now, and NEC recently announced plans to launch spectacles that allow voice-to-text translation.