Technology that could provide business travellers with speech to speech translations in six languages via wearable computers is being demonstrated this week.
Scientists at Carnegie Mellon University in the US are showing off the Web based planning application, in which six participants will speak in their six native tongues into the computers in locations around the world.
Each of their computers will use the technology to translate their text into another of the languages, then relay that data via servers in laboratories in the other locations.
A Web based travel guide and a global positioning system built into the wearable computers, along with translated directions from local residents, will be used to navigate around each location.
The demonstration is part of the Consortium for Speech Translation Advanced Research (C-Star) initiative, which also includes scientific institutions in Japan, Korea, Italy, France and Germany. It is designed to show breakthroughs in spontaneous speech translation, speech recognition and machine translation, such as 10,000 word vocabularies.
"Speech translation technology has matured to the point of allowing free, spontaneous dialogues using large vocabularies that can be translated into a variety of languages," said C-Star's chairman, Alex Waibel, professor at the university's School of Computer Science and the University of Karlsruhe in Germany.
"Earlier technology permitted only a limited vocabulary and demanded perfect syntax and speaking style," he said. "Speech recognition systems have been improved to handle the sloppy speech people produce when talking spontaneously to each other. The ums, urs, interruptions, hesitations and stutterings of spontaneous speech are automatically recognised, filtered and properly prepared for translation."
But some Web observers were sceptical about the process. "It's an interesting idea, but there are some instances where the device can't possibly work in 'real-time' [such as] translating from German to English on the fly," said John Grantham, an independent Web designer in Hanover.
"German has the rather odd habit of smacking verbs at the end of the sentence, often a long way away from the subject, whereas English prefers to have the subject and verb at the beginning of the sentence, especially in spoken English," he said.
Others pointed out that the announcement was sparse on detail and did not mention how the consortium had dealt with problems such as the monotonous sound of computer generated speech or colloquialisms.
There is the famous example of the program that translated the English phrase: "The spirit is willing but the flesh is weak," into "The vodka is good but the meat is rotten."
For more stories see this week's issue of PC Week UK
Latest Tesla news: Tesla share price continues to fall after Saudi Arabia's sovereign wealth fund is linked to investment in rival
SEC 'probe' takes its toll on Tesla as new research suggests that Tesla loses $6,000 on every $35,000 Model 3
RTX 280 Ti will come with 11GB of fast GDDR6 video RAM with a 352-bit memory bus offering 616Gbps
The scale of jobs lost to automation will be at least as large as those in the first three industrial revolutions
10nm Cannon Lake Core i3-8121U CPUs make a rare outing with Intel's NUC mini PC