Archives
 
 
 
  Special
 
 
 
  About Us
 
 
 

Newsletter
Free E-mail Newsletter from BYTE.com

 
    
           
Visit the home page Browse the four-year online archive Download platform-neutral CPU/FPU benchmarks Find information for advertisers, authors, vendors, subscribers Request free information on products written about or advertised in BYTE Submit a press release, or scan recent announcements Talk with BYTE's staff and readers about products and technologies

ArticlesDirect Speech-to-Speech Translation


October 1996 / International Features / You Said What? / Direct Speech-to-Speech Translation

Direct speech-to-speech translation aims to provide translation in real time for applications such as videoconferencing or automatic translation over the telephone. Although this seems like the next step in machine translation, the technology is still not mature enough for commercial products. But researchers persist. Organizations working in this field include the C-Star Consortium and the Interactive Systems Laboratory (ISL), a cooperative venture of the University of Karlsruhe in Germany and Carnegie Mellon University in the U.S.

C-Star includes companies and academic institutions from France, Germany, Italy, Japan, India, Korea, the U.K., and the U.S. In 1993, C-Star d emonstrated automatic interpretation over the phone in a series of bilingual experiments. That system required the speaker to talk very clearly and be grammatically correct, which humans normally don't do. C-Star II research aims to reduce such restrictions and create more robust interpreting systems that can recognize ordinary spontaneous speech, translate it, and turn it into synthesized speech. C-Star's goal is "multilingual speech-to-speech translation" in real applications by 1999.

The ISL's Janus speech-to-speech project deals with learning and handling new vocabularies in predefined situations, such as scheduling of appointments. It supports English, German, Spanish, Japanese, and Korean. The collaboration has developed a laptop-based speech translator that handles spontaneous, continuous, speaker-independent translation in limited domains. Translation output can be presented as synthesized speech or as text on screen or transparent goggles.

ISL has also develo ped a translating videophone station that allows one person to hear another's original voice and receive translations as subtitles or synthesized speech. When the speaker on one end makes a statement, the system returns a paraphrased version for verification. As soon as the speaker has verified it, the system translates the message and sends it to the recipient. Although the translation is not instantaneous, it allows for adequate straightforward communication.


Up to the International Features section contentsGo to previous article: Direct Speech-to-Speech TranslationGo to next article: Europe's Internet InfrastructureSearchSend a comment on this articleSubscribe to BYTE or BYTE on CD-ROM  
Flexible C++
Matthew Wilson
My approach to software engineering is far more pragmatic than it is theoretical--and no language better exemplifies this than C++.

more...

BYTE Digest

BYTE Digest editors every month analyze and evaluate the best articles from Information Week, EE Times, Dr. Dobb's Journal, Network Computing, Sys Admin, and dozens of other CMP publications—bringing you critical news and information about wireless communication, computer security, software development, embedded systems, and more!

Find out more

BYTE.com Store

BYTE CD-ROM
NOW, on one CD-ROM, you can instantly access more than 8 years of BYTE.
 
The Best of BYTE Volume 1: Programming Languages
The Best of BYTE
Volume 1: Programming Languages
In this issue of Best of BYTE, we bring together some of the leading programming language designers and implementors...

Copyright © 2005 CMP Media LLC, Privacy Policy, Your California Privacy rights, Terms of Service
Site comments: webmaster@byte.com
SDMG Web Sites: BYTE.com, C/C++ Users Journal, Dr. Dobb's Journal, MSDN Magazine, New Architect, SD Expo, SD Magazine, Sys Admin, The Perl Journal, UnixReview.com, Windows Developer Network