It wasn't too long ago that using online translator services such as Google Translate or AltaVista's Babel Fish seemed like the magic that would erase language barriers across the internet. Now Google is working on a new software that could translate voice input nearly instantly – as if sticking a Babel Fish into your ear.
Google already has a working text-to-text translation service as well a voice recognition system it uses for its phone software, including Google Voice.
"We think speech-to-speech translation should be possible and work reasonably well in a few years’ time," said Franz Och, Google’s head of translation services, in a Times Online story. "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."
The challenge now, besides reducing the lag between input and output, is improving accuracy of voice recognition. After all, the spoken word has more opportunities of variation compared to text.
"Everyone has a different voice, accent and pitch. But recognition should be effective with mobile phones because by nature they are personal to you. The phone should get a feel for your voice from past voice search queries, for example," said Och. "The more data we input, the better the quality."
Do you think a real-world Babel Fish could eventually take away the need for people to learn multiple languages?