KOMPAS.com - A mobile phone that can act as an interpreter is being developed by Google. The firm says its device will convert spoken words into another language almost instantly.
Franz Och, Google's head of translation services, said: '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.'
While early versions of Google's website translation software sometimes produced little more than gobbledegook, an ever-growing database has enabled it to achieve far greater accuracy.
So far it covers 52 of the world's estimated 6,000 languages, the latest being Haitian Creole. Google admits speech will be an even tougher challenge than text but says a customer's phone would adapt to its user by 'learning' their style of talking.
'Everyone has a different voice, accent and pitch,' said Mr Och. 'But recognition should be effective with mobile phones because by nature they are personal to you.'
And as with automatic text translation, what may begin as a fairly primitive technique will, Google hopes, become more sophisticated with the help of millions of users around the world. However language experts believe the prospect of such technology supplanting the ability to speak a foreign tongue is a distant one.
David Crystal, honorary professor of linguistics at Bangor University, said the problems of dealing with speed of speech and range of accents could prove insurmountable.
'No system at the moment can handle that properly,' he added.
In Douglas Adams's Hitchhiker’s Guide to the Galaxy, the Babel Fish was a small yellow creature capable of translating any language when placed in a person's ear.
It sparked a bloody war because everyone became able to understand what other people were saying.
Franz Och, Google's head of translation services, said: '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.'
While early versions of Google's website translation software sometimes produced little more than gobbledegook, an ever-growing database has enabled it to achieve far greater accuracy.
So far it covers 52 of the world's estimated 6,000 languages, the latest being Haitian Creole. Google admits speech will be an even tougher challenge than text but says a customer's phone would adapt to its user by 'learning' their style of talking.
'Everyone has a different voice, accent and pitch,' said Mr Och. 'But recognition should be effective with mobile phones because by nature they are personal to you.'
And as with automatic text translation, what may begin as a fairly primitive technique will, Google hopes, become more sophisticated with the help of millions of users around the world. However language experts believe the prospect of such technology supplanting the ability to speak a foreign tongue is a distant one.
David Crystal, honorary professor of linguistics at Bangor University, said the problems of dealing with speed of speech and range of accents could prove insurmountable.
'No system at the moment can handle that properly,' he added.
In Douglas Adams's Hitchhiker’s Guide to the Galaxy, the Babel Fish was a small yellow creature capable of translating any language when placed in a person's ear.
It sparked a bloody war because everyone became able to understand what other people were saying.