October 30th, 2005
Can your mouth become multilingual?
During a videoconference last week between Karlsruhe, Germany, and Carnegie Mellon University (CMU), Pittsburgh, USA, the talk of Alex Waibel, from CMU, was automatically translated in German and Spanish. Both the Pittsburgh Post-Gazette (PPG) and the Pittsburgh Tribune-Review (PTR) attended the conference, took pictures and were impressed by this new "open domain" speech-to-speech translation. This new computer technology is based on artificial intelligence (AI) and statistical methods. During the demonstration, the speaker had electrodes attached to his face and his neck, but the researchers think that these electrodes could be implanted into your mouth and your throat in a decade from now — if you agree of course.
This new speech-to-speech translation technology has been one of the hot topics discussed during the International Workshop on Spoken Language Translation 2005 (IWSLT 2005) which was held on October 24-25, 2005 in Pittsburgh. And here is the introduction of the PPG article.
[Szu-Chen] Stan Jou’s lips were moving, but no sound was coming out. Mr. Jou, a graduate student in language technologies at Carnegie Mellon University, was simply mouthing words in his native Mandarin Chinese. But 11 electrodes attached to his face and neck detected his muscle movements, enabling a computer program to figure out what he was trying to say and then translate his Mandarin into English.
The result boomed out of a loudspeaker a few seconds later: "Let me introduce our new prototype," a synthesized voice announced. "You can speak in Mandarin and it translates into English or Spanish."
What’s behind this new translation device?
What has made this possible has been a dramatic change in how computer translation programs are written. In the past, most translation software has been based on sets of rules — dictionary definitions, grammatical rules and such. In other words, programmers tried to make a computer think like a human.
But increasingly, the trend in artificial intelligence is to allow the computers to think like computers, using statistical methods to draw meaning out of masses of information, said Randall E. Bryant, dean of Carnegie Mellon’s School of Computer Science.
Of course, I’m sure that you think that this new technology doesn’t always provide correct translations. And, according to the PTR article, you’re right.
As Waibel delivered his lecture in English yesterday, the Spanish translation and English text appeared on the screen behind him — albeit with some glitches. For example, had the writer of this story relied on these translations for her notes, the word "diverse" would appear as "divorce" in this article and "potentially" would show up as "put tension."
[Note: Alex Waibel is the director of the international center for Advanced Communication Technologies, interACT, a joint center between the Universität (TH), Karlsruhe, Germany and Carnegie Mellon University, Pittsburgh, USA.]
A reporter for the Associated Press also noticed some mistakes.
During Waibel’s lecture, the translator erred sometimes transcribing his speech in English. The word "might" showed up as "mate," "some" as "sum" and "patent" as "patten."
Anyway, these systems will perform better and better. And they should become commercially available between five and ten years from now.
As Waibel told the PTR, "In the future, we could implant the electrodes into your mouth and throat if you want and have your mouth become multilingual."
Even if I would like to be understood by people who don’t understand me when I’m speaking in French, I’m not sure to like the idea to have electrodes implanted into my mouth. What about you?
Sources: Byron Spice, Pittsburgh Post-Gazette, October 28, 2005; Jennifer Bails, Pittsburgh Tribune-Review, October 28, 2005; and various web sites
You’ll find related stories by following the links below.
