Google developing Language Translation Phone!

Proud of the Nexus One's ability to convert speech to text? Get ready to have your minds blown - Google is developing a phone that translates languages instantly and provides an output. Like in Star Trek.

Not clear? In a nutshell - when someone talks to you in Aramaic, this phone translates the voice directly to Hindi so that you understand what the other person is saying. This is most definitely the Holy Grail of communication. "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 biggest challenge would of course be to reduce the lag time between the voice input and output and to improve the accuracy of the translation. "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."

Google already has an automatic system for translating text on computers - it covers 52 languages, adding Haitian Creole last week. Google also has a voice recognition system that enables you to simply speak commands into the phone rather than type. To develop the new live voice-translation technology Google is making use of the above mentioned systems, and their vast database of websites and translated documents. "The more data we input, the better the quality," said Och. There is no shortage of help. "There are a lot of language enthusiasts out there," he said.

Google's biggest challenge would, however, be tackling the hundreds of accents, dialects and slangs. "The problem with speech recognition is the variability in accents. No system at the moment can handle that properly." said David Crystal, honorary professor of linguistics at Bangor University. "Maybe Google will be able to get there faster than everyone else, but I think it’s unlikely we’ll have a speech device in the next few years that could handle high-speed Glaswegian slang. The future, though, looks very interesting. If you have a Babel Fish, the need to learn foreign languages is removed."