By Jo Twist
BBC News Online technology reporter
Small robots with friendly faces have helped out in the development of handheld translation gadgets to be tried out by travellers in Japan.
Papero has lent its translation ability to tourists
Visitors landing at Tokyo's Narita Airport will be able to hire a device which can translate the local lingo.
The speech-to-speech technology was developed by NEC, tested in Papero robots and then put in PDAs.
Papero is the first all-hearing, all-seeing robot to be able to talk in conversational colloquialisms.
The PDA hire scheme is part of a wider project, e-Airport, to make Japan's main international airport the most hi-tech in the world.
Lend me your brain?
As well as being able to understand and imitate human behaviour, Papero (Partner-Type Personal Robot), is the first robot to translate verbally between two languages in colloquial tongue.
It can cope, in other words, with slang and local chatter, and has a vocabulary of 50,000 Japanese and 25,000 English travel and tourism related words.
After Papero demonstrated its translation ability, the PDAs borrowed its brain and tongue. Users can talk into the device and it will talk back in almost-perfect Japanese in a second.
The e-Navi is meant to be a travelling companion for tourists
It has voice recognition, digital voice translation and a voice synthesiser to talk to users, explained Chris Shimizu, NEC's corporate relations manager, and the quality of the voice spoken back to users is much more human than robotic.
The devices also serve as mobile phones, and have airport and local guides, as well as unlimited wireless net access.
The development of this accurate speech-to-speech technology has been a result of joint research efforts from NEC in Japan and in Europe.
"The accuracy is dependent on the size and quality of the dictionary on the handset or PDA but is usually very close to 100% accurate," Mr Shimizu told BBC News Online.
Years have been spent developing the technology to cope with the challenge of understanding different speech patterns, accents and colloquialisms.
"The technology can pick these up straight away because of its understanding of linguistic inference.
"Also, it doesn't require a user to pre-register their voice."
Developments in the quality and accuracy of speech-to-speech, high speed translation technology could find its way into mobile phones soon too.
"Most certainly, it is absolutely ideal and it is most likely this technology will be utilised," said Mr Shimizu.
Business travellers and tourists can try out the PDAs before the scheme is offered commercially in other airports and tourist centres at the end of 2004.
Papero has been sent back to continue its old job as a personal companion to family members in Japanese homes.