November 18, 2005

War-Zone Test for Babel-Fish Tool

Funded by Darpa, the system would allow troops to communicate in Arabic through a laptop computer equipped with voice recognition and translation software. Troops could speak in English and have their words instantly translated into Iraqi Arabic, "spoken" by a computerized man's voice. The program also translates Arabic into English.

"Will it replace the need for an interpreter when you're having some sort of high-level conversation? Absolutely not," said Kristin Precoda, speech technology research lab director at SRI International and one of the developers of the program that got underway in May. "But it is absolutely to the point where it could be useful in some carefully chosen situations."

The effort to combine machine translation and voice recognition, a project Darpa calls TranTac, is an extension of earlier research spearheaded by SRI that culminated in the Phraselator. That device, essentially a PDA programmed to translate English phrases into other languages, is widely used by troops and medical workers in Afghanistan and Iraq.

But the Phraselator still has serious limitations, Precoda said. It can be impractical in countries with low literacy rates, such as Afghanistan. Additionally, many people are unfamiliar with the PDA interface.

Posted by Michelle at 03:51 PM | Comments (0) | TrackBack

November 04, 2005

Live speech-translation technology unveiled

Technology that provides live translation of speech from one language to another has been revealed by scientists from the US and Europe.

This and other translation technologies were demonstrated publicly for the first time at Carnegie Mellon University in Pittsburgh, US, last Thursday. They were developed by researchers from the International Center for Advanced Communication Technologies (InterACT), a collaboration between Carnegie Mellon and the University of Karlsruhe in Germany.

Posted by Michelle at 02:22 AM | Comments (0) | TrackBack

October 25, 2005

NEC Develops Speech-to-Speech Translation Software for Mobile Phones

NEC Corporation today announced that it has succeeded in the development of Japanese-English/English-Japanese, automatic speech translation software for single-chip multi-core processors for small devices such as mobile phones, capable of operation at high speeds with low power consumption.

Posted by Michelle at 07:08 PM | Comments (0) | TrackBack

October 21, 2005

Breaking Down Language Barriers

A good overview of the future of voice translation:

Speech-to-text and speech-to-speech translations present additional technical hurdles, because voice recognition must be added. Current voice recognition software has trouble getting even clearly spoken words correct. Just consider voice-activated customer calling menus. Nonstandard accents and background noise bring their accuracy down even further.

But Levin says the first systems, developed for "dirty travel survival," like using the cell phone to give cab drivers directions in Chinese, will be ready within two years. Levin is currently working on voice-to-text translations that will allow tourists to speak a question into their cell phones. Translated Chinese text will then appear on the cell screen for another person to read. True speech-to-speech translation, albeit with limited vocabulary, will be ready by the end of the decade.

Posted by Michelle at 12:47 AM | Comments (0) | TrackBack

September 20, 2005

TalkMan

Max, it's worth pointing out at this point, is a big blue bird, and he's the big heart of TalkMan. The idea is that you talk into a microphone attached to the PSP's USB slot, say what you want to say - to the girl on the bench, the waiter at the restaurant, the man at the checkout, the copper on the street, or whoever - and Max will translate it for you. There are various scenes (airport, hotel, shopping, etc.) and basic scenarios to pick from and each recognises various phrases - of which the game stores some 3,000 - and Max is not only capable of recognising them in four languages but also adding a bit of spark and emotion. You can even specify how forceful he is by setting the 'emotion level'.

Posted by Michelle at 12:39 PM | Comments (0) | TrackBack