Slashdot Mirror
Can Your Mouth Become Multilingual?
Roland Piquepaille writes "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 still doesn't solve the problem that automatic translators still have problems processing the logic of certain languages. Just look at babelfish.
Oh yeah. Please. Right now. Insert the electrodes into me right now. I can't wait!
Is it fascism yet?
Don't believe a word of this. Everybody likes to say they've finally cracked the problem of machine translation. This is exactly what we saw previously on Slashdot with the quote about the "bin Laden tapes" or whatever.
Proof? Ah, we'll get to that later.
Where in any of the links does it give the text of what he said, and the translation? And the analysis to the success of the translation? I found two sentences it mentioned. That's not good enough. Let's allow independent examination of the success of this translation.
Rank my idea: http://www.sinceslicedbread.com/node/531
So I won't even have to use a phone to get my speech intercepted, The Bad Guys [tm] now can directly wiretap my mouth. Perhaps this can be intercepted by chewing on my tinfoil hat?
Life is just nature's way of keeping meat fresh.
Computers have a hard time translating written things as it is... any bilingual will tell you that online translators for complete sentences will do nobody any good, for the most part. My Spanish teachers are all able to see papers with computer translations very easily, due to similarities in words and meanings (such as the word "pants" which can be colthing or breathing heavily) Not to mention, grammar and things like that are not done well at all. For the fun of it, try going to an Online translator and write something in English, translate it to Spanish, then back to English. Some results are pretty crazy. I guess the point I'm trying to make is this: what makes the translators so special compared to the ones we have now? How can they work better? Sure, there is probably a bit more effort put into these, but I don't think that a good translator will be available for another 5 years, not to mention the whole "take the speech you aren't saying" thing is hard to believe.
Another approach is from some work I saw demoed at an MIT conference in Vienna. If you capture enough video of a person speaking, you can remix/rerender video of that person saying anything you want them to say. The software works at the phonetic level so you can even synthesize words that the person has never even uttered before and even make them appear to speak languages that they don't know. They had some visually convincing video showing people saying things that the researchers claimed they never said. Yes, the demo version worked with clean test video and a professional video/image analyst could probably spot a faked/remized video. But if these technology becomes good enough, I can see it making video a nontrustworthy source of data (like skillfully retouched photos).
Two wrongs don't make a right, but three lefts do.
If construction was anything like programming, an incorrectly fitted lock would bring down the entire building...
I am currently taking a great course on the Introduction of Linguistists. I have been exposed to the rather complex process a human being uses to make a sound (phoneme). You can go here to get a good idea of what it truly entails http://ocw.mit.edu/OcwWeb/Linguistics-and-Philosop hy/24-900Spring-2005/CourseHome/index.htm
The main obstacles to this is the fact each langauge uses different places and manners of articulation as well as the fact that intonation can change the meaning of a word. In Mandarin the word ma can change meaning based on tone.
This is not a factor in English but certainly is for most Asian languages.
The ability to use phonemes is one thing but paralinguistics is another (sarcasm).
If you're interested in reading the actual research paper involved (as opposed to a journalist's interpretation), it's readable here - pdf file, but lots of graphs, tables and pictures, so I'll forgive them.
it's about speech recognition. They've identified a new source of data for identifying phonemes, one that apparently provides cleaner output than working from the audio. Dollars to donuts the resulting words are then just popped into a Babelfish-equivalent.
This is interesting and important work, but the translation angle is really just one potential application of the technology.