Google developing speech-to-speech translation for mobiles
Source: The Times (UK)
This sounds pretty cool to me. I got the opportunity to play around with a friend’s Nexus One cellphone the other day, and one of the best features was that at any point there was a keyboard on the screen, I could choose to press a little microphone button and speak what I wanted to type. It wasn’t exactly foolproof, but it seemed like an excellent integration of speech-to-text.
However, Google are now claiming that soon they will have finished developing speech-to-speech translation software for mobile devices; which will enable users to speak what they want to translate into the handset and have a live translation, anywhere.
We think speech-to-speech translation should be possible and work reasonably well in a few years’ time.
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. If you look at the progress in machine translation and corresponding advances in voice recognition, there has been huge progress recently.– Franz Och, Google’s head of translation services
Since they seem to have a pretty good footing in the speech-to-text translation, but it could still be better. I’m looking forward to when we have universal translation with the whole Babelfish-on-your-phone setting, but I wonder how it will affect language learning in general – will people still want to learn German for a vacation to Germany if they can just use their phones to get directions, order in a restaurant, and deal with pretty much any other situation?
Probably not. But even early implementations of this software will be a great failsafe if you need direct translation, then and there. Google does it again…