×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Google Shooting For Smartphone Universal Translator

ScuttleMonkey posted more than 4 years ago | from the ford-why-is-this-fish-in-my-ear dept.

Communications 178

nikki4 writes to tell us that in giving some major improvement tweaks to its existing voice recognition tool for the Smartphone, Google is aiming for new translator software that will provide instant translation of foreign languages. "The company has already created an automatic system for translating text on computers, which is being honed by scanning millions of multi-lingual websites and documents. So far it covers 52 languages, adding Haitian Creole last week. Google also has a voice recognition system that enables phone users to conduct web searches by speaking commands into their phones rather than typing them in. Now it is working on combining the two technologies to produce software capable of understanding a caller’s voice and translating it into a synthetic equivalent in a foreign language."

cancel ×
This is a preview of your comment

No Comment Title Entered

Anonymous Coward 1 minute ago

No Comment Entered

178 comments

Google is not far from Engrishisfunny.com... (5, Funny)

zero_out (1705074) | more than 4 years ago | (#31066088)

Maybe my experience is atypical, but Google doesn't seem to translate pages very well. I can only imagine how bad it will be having a phone do this. "Did that guy's phone just call me what I think it did?"

Re:Google is not far from Engrishisfunny.com... (4, Insightful)

amRadioHed (463061) | more than 4 years ago | (#31066460)

Considering that human languages follow rules that are as convoluted and transient as Calvin-ball I'd say they do an admirable job. Machine translation is really an amazing challenge.

Re:Google is not far from Engrishisfunny.com... (2, Informative)

zero_out (1705074) | more than 4 years ago | (#31066520)

As someone with a background in AI and HCI, I completely agree. Unfortunately, we still have a long way to go, and I think that Google is jumping the gun on this. It should prove to be quite humorous, even as first steps go.

Re:Google is not far from Engrishisfunny.com... (1)

Facegarden (967477) | more than 4 years ago | (#31066674)

As someone with a background in AI and HCI, I completely agree. Unfortunately, we still have a long way to go, and I think that Google is jumping the gun on this. It should prove to be quite humorous, even as first steps go.

Well, to be fair, they did say this would be something they are shooting to accomplish "In a few years". Still a tough task, but they're giving themselves some time. Considering how far they've gotten so far, I'm really excited to see how this works out.
-Taylor

Re:Google is not far from Engrishisfunny.com... (4, Insightful)

greenguy (162630) | more than 4 years ago | (#31067192)

As a professional translator and interpreter, I also agree that Google has done better than anyone else, and that that's still not particularly good by objective standards. I've been using their Translation Center (NOT Google Translate) for a while now, and I've seen their translation memory evolve before my eyes.

The basic problem, however, is that the computer doesn't actually understand what it's spitting back to you. It only spits back the translations others have provided for similar phrases. It doesn't know if they're any good. Sometimes they're surprisingly good, and sometimes they're bizarrely bad.

There's a lot of ambiguity in human writing, and even more so in speech. Even assuming you hear the words correctly, it's tricky to tease out the precise meaning they wanted to convey, and trickier still to re-express that in another language, with appropriate cultural and regional context.

Google will get better and better at parroting good translating and interpreting decisions, but software will never be able to make those decisions, because, in the final analysis, they are subjective decisions.

Re:Google is not far from Engrishisfunny.com... (1)

timeOday (582209) | more than 4 years ago | (#31067394)

Google will get better and better at parroting good translating and interpreting decisions, but software will never be able to make those decisions, because, in the final analysis, they are subjective decisions.

Think about how successful google has been with search. Prior to the web, we would have idealized search as speaking with an expert who has all the knowledge that exists on the web. Various efforts still strive for that vision today (askjeeves, wolphramalpha, etc). But clearly it is unreachable for the forseeable future. Yet, search is very useful.

Similarly, this universal translator may well reach a point that it is possible to visit a place, buy things, have a meal, ask where the toilets are, and get back home, particularly when both parties in the conversation are familiar with the limitations of translation. That would be extremely useful, even if it's only 1/100 of all a native bilingual speaker understands, or what you would need for nuanced treaty negotiations or to author a respectable translation of War and Peace.

Re:Google is not far from Engrishisfunny.com... (0, Offtopic)

Iron Condor (964856) | more than 4 years ago | (#31067280)

[...]I think that Google is jumping the gun on this. [...]

Funny that you should mention a gun there - because guns are already-existing universal translators. They can deliver only one message, but they can say it in every language conceived of by man. Just sayin...

Re:Google is not far from Engrishisfunny.com... (1, Interesting)

Anonymous Coward | more than 4 years ago | (#31067078)

Yes, but it doesn't actually work yet. Not even close. I can't even call the local taco place with Google's voice search on my Blackberry. It's a joke, and correcting it takes MUCH longer than keying in "baja fresh" with the chicklet keyboard.

Re:Google is not far from Engrishisfunny.com... (0)

Anonymous Coward | more than 4 years ago | (#31066478)

I'm sure they'll improve over time.

I for one welcome our new tricorder-wielding universal translator overlords.

- Signed, kjharry@itsfast.net

What could possibly go wrong? (0)

Anonymous Coward | more than 4 years ago | (#31066544)

[From the rocket ranch] I await your instructions sir.

a) [From HQ] Don't fire the missiles!

or

b) [From HQ] Don't. Fire the missiles!

What could possibly go wrong?

Re:Google is not far from Engrishisfunny.com... (0)

Anonymous Coward | more than 4 years ago | (#31066572)

..
When you're around, I'm so elated I want to dance!

=

MY HOVERCRAFT IS FULL OF EELS

Re:Google is not far from Engrishisfunny.com... (1)

Kijori (897770) | more than 4 years ago | (#31066630)

Maybe my experience is atypical, but Google doesn't seem to translate pages very well. I can only imagine how bad it will be having a phone do this. "Did that guy's phone just call me what I think it did?"

If you haven't used it recently, try it now. Speaking as a linguist I am incredibly impressed by the speed of their progress.

Re:Google is not far from Engrishisfunny.com... (1)

IANAAC (692242) | more than 4 years ago | (#31066860)

If you haven't used it recently, try it now. Speaking as a linguist I am incredibly impressed by the speed of their progress.

And speaking as a translator, I can say my job is in no danger.

But putting that aside, it's rather absurd to even compare text-to-text with speech-to-speech processes; they're entirely different beasts. I routinely get messages left through my google voice account in non-english languages, and the text that is left in my inbox is ridiculously bad. If they can't even get voice-to-text right without even going through a translation, they've got a LONG way to go.

Re:Google is not far from Engrishisfunny.com... (1)

Syntroxis (564739) | more than 4 years ago | (#31066874)

They don't seem to be able to transcribe Google Voice messages very well, and they are in English. I am, however, amazed that they can transcribe voice messages at all.

Re:Google is not far from Engrishisfunny.com... (1)

Hes Nikke (237581) | more than 4 years ago | (#31067104)

From my Google Voice transcription:

Schedule he left in my house. I got your Gardner here. Remax Logo, we wanna get back to movie. Gimme a call. Projects.

lol what?

Or... (3, Funny)

fatherjoecode (1725040) | more than 4 years ago | (#31066092)

Or you could just stick this Babel fish in your ear.

Re:Or... (1)

nicknamenotavailable (1730990) | more than 4 years ago | (#31066316)

Oh freddled gruntbuggly?thy micturations are to me
As plurdled gabbleblotchis on a lurgid bee.
Groop I implore thee, my foonting turlingdromes.
And hooptiously drangle me with crinkly bindlewurdles,
Or I will rend thee in the gobberwarts with my blurglecruncheon,
see if I don't!

That's the first thing I'm gonna try translating, if and when I get to use this.

(I hope the warranty covers everything)

Or simply phone one of the translation services (1)

Colin Smith (2679) | more than 4 years ago | (#31067170)

There are companies who have translators available on the phone. You call them, tell them what you want to say and they can talk to the other person. I don't recall it costing too much.
 

Why bother for now? (1)

the roAm (827323) | more than 4 years ago | (#31066094)

Translation software sucks hard, even under simple phrases. Why do it on a cellphone on a large scale?

Re:Why bother for now? (4, Insightful)

PPalmgren (1009823) | more than 4 years ago | (#31066240)

Google is in the business of collecting data and applying it to practical problems. I imagine the voice-to-text will be vastly improved over its generations by users accepting/rejecting the vtt result and them pooling the results data. The same thing could be done for translation from one language to another.

I see it as crowdsourcing the algorithm accuracy checks among millions of people, allowing them to improve the algo at a much faster rate than they (or their competitors) would otherwise be able to do in a closed testing environment.

This is all speculating on the fact that google pools results of translations or VTT and whether the user accepts/declines them. I wouldn't be surprised in the slightest if they did.

Re:Why bother for now? (1)

Idbar (1034346) | more than 4 years ago | (#31066570)

Translation software is difficult to absorb even a simple sentence. What is a mobile phone?

I enjoy going back and forth between languages. Go to Arabic, Korean, Chinese or sometimes Spanish and back, to realize it still needs some work.

parent (0)

Anonymous Coward | more than 4 years ago | (#31066688)

translated to arabic, korean, spanish and back:

I play back and forth between languages. In Arabic, Korean, Chinese, Spanish, or in some cases, back, back and still needs some work to do.

Re:Why bother for now? (1)

Monkeedude1212 (1560403) | more than 4 years ago | (#31066724)

You push it more into the public eye, the public critiques, investors spend money to make a better product, a better product gets made.

You didn't think there are any actual entrepreneurial software developers out there who worked for free did you?

Re:Why bother for now? (1)

snowtigger (204757) | more than 4 years ago | (#31066794)

Google is working on a translation system that's based on the massive information they've gathered off the internet. To get an idea of how this works, have a look at the 2009 Google Wave developer presentation. Fast forward to about 1h 12min
http://www.youtube.com/watch?v=v_UyVmITiYQ [youtube.com]

In another demo (which I can't find right now) they show how the translation engine understands the context of the conversation.

It's easy to see how this could be applied to a phone call using the right voice recognition software.

Re:Why bother for now? (1)

Ungrounded Lightning (62228) | more than 4 years ago | (#31067398)

Why do it on a cellphone on a large scale?

Because a cellphone is a portable communications device and a modern one has major compute power and storage, thanks to decades of Moore's Law. Adding a translation application to such a platform - even if an only moderately competent one - is a natural fit and a potentially major benefit to the user at negligible cost to the provider.

If it's anything like Google Translate (3, Insightful)

slyborg (524607) | more than 4 years ago | (#31066096)

...this is a recipe for universal worldwide hilarity.

Re:If it's anything like Google Translate (4, Interesting)

sakdoctor (1087155) | more than 4 years ago | (#31066444)

I tried to translate your sentence multiple times, then back to English so I could post the ridiculous result.

Except google's translation was actually pretty good.

Re:If it's anything like Google Translate (1)

Stween (322349) | more than 4 years ago | (#31067020)

"I was twice an hour at least, I had to translate English text to disastrous results."
http://translationparty.com/#6414445 [translationparty.com]

Re:If it's anything like Google Translate (0)

Anonymous Coward | more than 4 years ago | (#31067318)

I translate the sentence several times, and then try the UK, the results so I had to be really stupid.

Bet it was the Slavic to Korean that did it.

Re:If it's anything like Google Translate (4, Interesting)

Tetsujin (103070) | more than 4 years ago | (#31067248)

I tried to translate your sentence multiple times, then back to English so I could post the ridiculous result.

Except google's translation was actually pretty good.

Try a more complicated example. For instance, starting here:

"It's probably pretty good at translating translations it produces back into the same source text. If you figure that a phrase structure in one language corresponds to a certain data structure in Google Translate, then it makes sense that this data structure would survive multiple passes through the same restructuring algorithm..."

translating to Japanese and back to English yields this:

"It is translated to produce translated text back to the very same source is probably a good thing. Cases, one single phrase structure of language specific data structures in the Google translation, it is this data structure makes sense and survival of multiple paths through the same algorithm structure corresponding figures ..."

Here you've got badly handled idiomatic phrases all around... Like the Google translation to Japanese used "seiseisuru honyaku no honyaku dewa ii koto da" at the end of the first sentence ("created-translation's translation is good" or something like that). On the translation back the connection between "good" and "translation" was lost - Google slapped on a fairly generic "is probably a good thing" - picking the bit of uncertainty out of the start of the Japanese sentence and combining that with the "dewa ii koto da" - but dropping the whole idea of what it is that's good... Which is something that can be kind of vague in the structure of Japanese... Meanwhile, the phrase "source text" was transliterated into katakana, but it got broken up in the translation back to English and wound up in two different locations in the sentence...

The whole conditional clause in the second sentence got kind of mangled. In the Japanese translation it starts with "baai wa": baai means "case" or "situation" - the structure of the sentence establishes this "case" being described as a possibility... Google lost all that, and just said "cases," Then, at the end of the sentence, after the ellipsis, "figure", from "if you figure" in the English original, was tacked on as "taiousuru zu" - "interacting drawing" or "interacting figures". In the return-to-English version this somehow wound up back before the ellipsis again.

The rest of the second sentence in Japanese is something like "if this data structure uses the same intermediary algorithm, several passes of the algorithm should be survived and it should make sense." The apparent problem there is something analogous to operator precedence in arithmetic. The "and" is meant to mean that the surviving translation should still make sense - but this clause apparently got broken up... like the reverse translation assumed that "uses the same intermediary algorithm... should be survived" was all one stand-alone clause - and so it assumed that clause had nothing to do with "this data structure", switched the order of the "and" around, etc...

My hobby is building Gundam models - one of the most comprehensive review sites for new Gundam kits is in Korean. Believe me, we all try using Google translate or Babelfish on Dalong's site from time to time, but the result is rarely worth the effort.

Re:If it's anything like Google Translate (0)

Anonymous Coward | more than 4 years ago | (#31067508)

If you like the Google translation is a universal recipe for hilarity in this world.

Re:If it's anything like Google Translate (2, Interesting)

jellomizer (103300) | more than 4 years ago | (#31066708)

The article... Converted from English to Hindi back to english...

Google is developing software, the first foreign language translation of a phone almost immediately - Hitchhiker Guide's may sound like a fish galaxy.

Building on existing technology, speech recognition and automatic translation by Google is expected to have a basic system ready in a few years time. If successful, it's finally over 6000 languages in the world can be translated into the interaction between.

The company has set up an automated system, more than 1 million text translation of multilingual websites and computer scanning of documents are silent. So far in the 52 languages, along with last week's cover, Haitian Creole.

Google also has a voice recognition system that mobile phone users to order their mobile phones to talk, rather than type them in. Steering allows Web searches

Links
Fear, Google and a coalition Spiveyr Main
Village mob obstructed Google Street View Car
Now, these two software for the caller's voice is to understand the joint production technology, and a foreign language into a synthetic equivalent. Like a professional human translation, cell-phone speech "package" analyze, listen to lectures, the words and phrases until it understands the full meaning, and then try to translate. ,, Translation service, Google's head, Franz Och "We think speech, voice translation as a few years time as possible to work should be appropriate 'said.

"Obviously, it's easy work, you need to combine high precision machine translation and speech recognition accuracy, which is currently what we are doing.

"If you see progress, and machine translation, speech recognition, the same advances recently there has been significant progress."

While automatic text translation, it is very effective, voice recognition to prove more challenging.

, Och "everyone a different voice, accent and tone is" said. "While recognizing that the mobile phone, as they should be effective by nature you personally. Phone should feel your voice last a voice search query, for example."

Translation software may be more accurate and use it. Translation system using crude Though some regulations - based on language syntax, Google their vast database, website, and translation of documents for use to improve the accuracy of your system.

"We have more data entry, quality, good," Och said. There is no shortage of help. "Many are language enthusiasts," he said.

However, some experts believe that life is still high barriers are translated. , Honorary professor of linguistics, David Crystal, Bangor University, said: "The problem with voice recognition is a difference of accent. System currently can not handle.

"Maybe Google will quickly than others to access, but I think this is not possible, in the next few years we will have a speech tool can handle a high speed cannot Glasgow.

"In the future, but it looks very interesting. If you have a noisy fish, learning a foreign language should be deleted."

Milky Way galaxy, the small, yellow for any type of sound fish language translation capabilities, the Travel Guide in Cannes kept. It started a bloody war, because everyone other person can understand speech.

Warning Label (4, Funny)

Ukab the Great (87152) | more than 4 years ago | (#31066100)

Caution: not for use with Hungarian Tobacconists.

Re:Warning Label (0)

Anonymous Coward | more than 4 years ago | (#31066422)

Drop your panties, Sir William; I cannot wait 'til lunchtime.

Re:Warning Label (0)

Anonymous Coward | more than 4 years ago | (#31066816)

From English to Hungarian then to German then back to English and Google says....
Caution: Do not use Hungarian tobacco shops.

My Phone Has Android (0)

Anonymous Coward | more than 4 years ago | (#31066136)

My phone has Android. It's very neat but, not terribly practical. It includes voice dialing and voice Google search. It is slow, taking several seconds to record, upload and translate the voice to text. Then of course, you have to do it all over again because it completely botched the interpretation. Result: Time wasted!

Now they want to do language translation as well? They can't even get a single language right and they want to do multiple languages? Even their existing Language tools page is very neat and often handy but, the results are typically very dodgy.

The fantasies of Star Trek universal translators are still WAY off.

Re:My Phone Has Android (0)

Anonymous Coward | more than 4 years ago | (#31066466)

I see the sentence "My phone has Android" and I parse it the same as "I can has cheezburger". I guess my brain is about 3 years behind the curve.

Re:My Phone Has Android (0)

Anonymous Coward | more than 4 years ago | (#31066768)

You have to speak clearly. Duh!

Mumbling gibberish like a moron, you should expect to get shitty attempts. Hell, if people can't even understand you, how the hell is a computer going to have a chance?! Fucking douche!

Wasn't the Star Trek universal translator ... (1)

Ungrounded Lightning (62228) | more than 4 years ago | (#31067330)

... a partially telepathic device, rather than a pure computer program? (And invented by Spock's mother - a scientist who ended up marrying a high-ranking (and of course telepathic) Vulcan she encountered during her research?)

I THINK that was cannon rather than fan fiction...

Will it make call centers in India bearable? (0)

Anonymous Coward | more than 4 years ago | (#31066146)

Maybe this technology will make dealing with call centers in India somewhat bearable. Perhaps it'll be capable of converting their dialect of "English" into something that the rest of the English-speaking world can understand.

Then again, this translation technology probably can't do a damn thing about their general lack of knowledge. Shucks.

State of voice recognition (4, Insightful)

qoncept (599709) | more than 4 years ago | (#31066168)

Does anyone use voice recognition software? Here are a couple of my voicemails transcribed by Google Voice:

Hey man, Hello, this is gonna ask you about Stockton uncle in a missed your call, so, so give well. Okay bye.

Hey it's me and I for me. Long, My of the day. So Hey Jared, Here doing. If you come for another anti, gimme a call before you go to sleep and stuff, so give me a favor you familiar with it. I love you bye.

Re:State of voice recognition (1)

rsborg (111459) | more than 4 years ago | (#31066354)

I find Dragon to be much better, simply because they require you to upload your contact list (privacy issue flared up a while back but their new privacy agreement is pretty in-depth and satisfactory for me), so any contacts are not garbled, like they were in GVoice voicemail->text (a feature I love, but is definitely not for the easily confused).

I'm sure if Google used their contacts list (from your google voice or gmail contacts) privacy freaks would rip them a new one... so not sure what they can do other than to walk through that firestorm.

Ultimately, finding context using a particular person's lexicon is a massive privacy breach, but would be required for our computers to really talk with us... noone has the same idiomatic expressions, so a catch-all solution without machine-learning is bound to be lackluster.

Re:State of voice recognition (1)

ottothecow (600101) | more than 4 years ago | (#31066594)

Google voice has definitely gotten better at recognizing my name after accepting/rejecting voicemails and filing a feedback request (right near the beginning).

The thing I have noticed is that it is a little too trigger happy to label the first bit of audio as a standard greeting (hello or something). I have a friend who seems to manage to *never* start a voicemail with an immediate greeting. There is always like a giggle or some background sounds or a last word or two of conversation with a real person. GV seems to always tag the first two syllables as "hello" and then get really messed up on the transcription when it gets to the part where she actually says hello...from there the rest of the message just comes out garbled.

Re:State of voice recognition (1)

Joe Tie. (567096) | more than 4 years ago | (#31066376)

I suspect your friends might have thick regional accents. The voicemail transcriptions are the main reason I use it. Perfect, no. But I'd say it usually only messes up about one or two words per paragraph of text, on average. Except for one friend with a really noticeable Texas accent. It has serious trouble with his.

Re:State of voice recognition (1)

qoncept (599709) | more than 4 years ago | (#31066438)

I live in the midwest and my friends (at least in the case of these voicemails) are intelligent and well spoken. They weren't talking as though they were going to have a computer interpret what they were saying, but aside from that they were speaking about as clearly as you could hope for.

Re:State of voice recognition (0)

Anonymous Coward | more than 4 years ago | (#31066468)

Hey man, Hola, esto va a preguntarle acerca de Stockton, en un tío perdido a su llamada, así, así que bien. Bueno adiós.

Hey, soy yo y yo para mí. Long, My del día. Así Jared Hey, aquí haciendo. Si viene por otro anti, dame una llamada antes de irse a dormir y todo eso, así que me da un favor a usted familiarizado con él. Te amo bye.

There! You just needed to put it in Spanish! Now it makes absolute sens.... uhm...

Re:State of voice recognition (1)

thetoadwarrior (1268702) | more than 4 years ago | (#31066492)

It doesn't work that bad for people with a clear accent. The problem is getting the software to work as well with Southerners from the US or Scottish people. But I am glad Google is continuing to work on it despite it it not being perfect.Someone has to keep pushing it if it's going to improve.

Re:State of voice recognition (1)

Locke2005 (849178) | more than 4 years ago | (#31066504)

It is common for voice recognition software to confuse homophones, since it doesn't recognize context. But that's ok, I know you _really_ meant to say, "I love you bi!"

The problem with voice recognition (1)

msimm (580077) | more than 4 years ago | (#31066632)

The problem with voice recognition is inherently a user related problem. All this fluid/casual conversation, regional dialects, muffled voices, uneven, laxidasical cadences not to mention you kids and your fads and lexicon of so-called 'lingo'. If everyone just spoke like robots there'd be no problems. Humph!

Re:State of voice recognition (1)

travisb828 (1002754) | more than 4 years ago | (#31066648)

This reminds me of when we launched a speech IVR at work. When it was first launched the Spanish portion couldn't understand a native Spanish speaker. It would only understand someone speaking Spanish with an English accent. The reason for this behavior was the fact that it was tested and built its Spanish profile based on native English speakers. It took a week for it to learn how to understand Spanish spoken by native Spanish speakers.

Keep in mind that a speech IVR has a limited number of utterances. To do something where any speech can be transcribed cleanly into text, translated into language x, and then read back by TTS in close to real time is impressive. From Google's perspective they need a wide range of people transcribing voice mail and calls into text just to build a decent sample of how the population speaks. This is one of those things that only improve with more usage.

Re:State of voice recognition (1)

Monkeedude1212 (1560403) | more than 4 years ago | (#31066656)

Speech to text can be so perfectly on the mark sometimes (when you expect it to be way off) and it can be way off on something so simple.

My girlfriend is a history major and she always handwrites her papers - and because I can get 70 WPM (bursts, not constant) I usually end up typing them up for her. I decided we'd try the Speech to text service on my laptop, with the USB microphone that came with Rockband.

The paper was on Women in Ancient Rome, so you can imagine that there would be a ton of errors when it comes to names and such. Octavia, Caesar, Antony, not things in common language.

Anyways, 95% of the paper was bang on perfect. The voice recognition technology makes you go through about a dozen test sentences to help analyze your speech, something I figure Google voice recognition doesn't do when you leave a voicemail.

It was pretty funny though, it went from a perfectly and completely comprehensive sentence explaining the heirarchy of women in the Roman Culture and how the noble women were an influence, to a sentence that read (to the best of my knowledge; Oh Octavio, on two they could sparse a little brain and then some. I believe the sentence had to do with a library that Octavia had started (though I can't remember its exact wording).

Via Stephen Fry... (4, Interesting)

Sockatume (732728) | more than 4 years ago | (#31066748)

Stephen Fry offers... [stephenfry.com]

"Hi, Stephen, it’s Natasha from BBC Newsnight in London. Just to say I’ve sent you two texts. One is to say that we could do it at eleven am your time after the launch, or any time sooner after the launch, or we could do it at midday as we suggested earlier. I, er, if you could text me back about that, and I’ve sent you the details of Skype that you need to do too. If you could give me a call back. Enjoy the launch and I’ll speak to you after that. Thank you Bye."

I’ve transcribed it from the voicemail sound file that resides online on my inbox on the Google Voice site. All fine. I have also ticked the option for Google Voice to send me a text transcript of any voicemail. Below is their interpretation of Natasha’s message it’s rather endearing how hopelessly wrong the largest company on earth gets it.

"Hi Stephen. It’s Jeff from BBC needs in nuns. And just to say I sent 80 tax, one, if to say we could do it. I left in i a m your time off to go into any time soon, or the court and full we could grab me today as we suggested at. A. F. I. If you could text me back byebye. I’ve sent you the details of skylights that you need to 3 T if you could give me a call. Bye. Enjoy the loans. I’ll speak to you after that. Thank you. Bye"

On a more serious note, such transcripts at least allow you to get an idea of the rough content and tone of a message without having to stop and listen to it, a much more concentration-intensive task.

Re:State of voice recognition (1)

JustinOpinion (1246824) | more than 4 years ago | (#31066944)

I use voice recognition all the time. Lots of people do. I use the voice-search on my Droid. You have to enunciate fairly clearly, but it's faster than typing. And when it's wrong, that's fine--you type it out instead. I also use Google Voice transcriptions. Are they perfectly correct? Heck no. They have tons of mistakes. But the transcription is accurate enough that one can glance it over and immediately know the general subject matter of the voicemail, which immediately tells you if you need to: (1) call the person back; (2) listen to the voicemail for more detail; or (3) ignore it. This is a huge time-saver. The transcription is also very good with numbers, which means that when people spell-out phone numbers for you to call, they show up correctly in Google Voice, and can even be clicked on to call! These features are useful.

My point is this: voice recognition doesn't have to be perfect to be useful. It's just like doing a Google search. Does it always return exactly the page you wanted? No. Are the results useful? Almost always. It's a shift in thinking, from "AI research is about creating truly thinking machines" to "let's make simply, faulty systems that give the right answer often enough that they are useful."

Things like modern search engines, voice transcription, spellcheck, predictive auto-complete, etc. are all examples of things that are inherently faulty, and yet extremely useful (as long as you're aware of their limitations).

Re:State of voice recognition (0)

Anonymous Coward | more than 4 years ago | (#31067256)

Google Translate between English, French, German, Spanish is absolutely amazingly good. Anyone criticizing it has not tried it recently. The reason why those translations are now very good is because Google has enormous amounts of professionally translated texts from the European Union and the United Nations, where by just adding more and more examples to Google's database, the translations become better and better.

Also, Google can use their search technology to analyse the probable context of every bit of translation. Thus increasing the probable quality.

Of course you do get errors in the translation because of lack of understanding of the context. But then, Google could add more and more human corrections of automatic translations, by adding such features in online forums, this way Google will get even more understanding of context for translations.

Anyone doubting voice recognition needs to try Dragon Naturally Speaking or however they are called. Those software are absolutely amazing for native English speakers, those who don't have too bad an accent. The problem is that voice recognition is mainly only good in English because Billions of dollars have been invested in English speech recognition, while all other languages have had much less investment in creating precise voice recognition.

I look forward to Google automatically generating subtitles to all Youtube videos on-demand, and automatically translate all subtitles in all other languages. For that, Google could take in human corrections by all Youtube users, when there are errors in the voice recognition or in the translations. This way, a popular Youtube video will likely have that many viewers that even if only 0.01% of the viewers contribute in checking and correcting the subtitles, that would still be enough to have near perfect subtitles for such popular videos in all languages. And by the human corrections, Google can learn and become better at making the automatic ones.

Next step, injection (1)

endlessoul (741131) | more than 4 years ago | (#31066184)

Sure, these will be handheld. But in the future, they'll be directly injected into you by a DRD.

Re:Next step, injection (1)

robably (1044462) | more than 4 years ago | (#31066532)

For anybody elkse wondering what DRD stands for, I looked it up and it means Discrete Rectal Dongle.

Have to agree (1)

Deflagro (187160) | more than 4 years ago | (#31066186)

with everyone else... Google isn't great at translating and sadly it's pretty much the best. I speak a myriad of languages and Google only does well with Latin based langs and only if they are grammatically perfect.
You could always figure it out by context but when you get to German or Russian, then you're in trouble. Hell, imagine Mandarin/Cantonese? Pretty soon though, everyone will be able to understand everyone else and I won't be as cool anymore :)

Yes! Bring back the joy of Tablespoons! (4, Interesting)

argent (18001) | more than 4 years ago | (#31066290)

Tablespoons, by an Apple Newton

or [allegedly] what happens when you run Jabberwocky through a handwriting recognition program.... :-)

-----------

Teas Willis, and the sticky tours
Did gym and Gibbs in the wake.
All mimes were the borrowers,
And the moderate Belgrade.

'Beware the tablespoon my son,
The jaws that bite, the Claus that catch.
Beware the Subjects bird, and shred
The serious Bandwidth!'

He took his Verbal sword in hand:
Long time the monitors fog he sought,
So rested he by the Tumbled tree,
Long time the monitors fog he sought,

And as in selfish thought he stood,
The tablespoon, with eyes of Flame,
Came stifling through the trigger wood,
And troubled as it came!

One, two! One, two! And through and through,
The Verbal blade went thicker shade.
He left it dead, and with its head,
He went gambling back.

'And host Thai slash the tablespoon?
Come to my arms my bearish boy.
Oh various day! Cartoon! Cathay!'
He charted in his joy.

Teas Willis, and the sticky tours
Did gym and Gibbs in the wake.
All mimes were the borrowers,
And the moderate Belgrade.

Uh oh (1)

eln (21727) | more than 4 years ago | (#31066320)

Google's voice recognition software combined with Google's translation software. I predict this will cause World War III within hours of going live.

Why don't they make something PRODUCTIVE (1)

Shadow of Eternity (795165) | more than 4 years ago | (#31066358)

Like a f#@%ing deflector dish, then we can solve all the world's problems by reversing the polarity once it's constructed.

Re:Why don't they make something PRODUCTIVE (1)

toastar (573882) | more than 4 years ago | (#31067084)

No no no. the trick is to Bounce a graviton particle beam off the main deflector dish.

Google translation (0)

Anonymous Coward | more than 4 years ago | (#31066368)

Lets hope it works a bit better than their browser translator, I always bet an error!

Won't work but misunderstandings should be funny (1)

syousef (465911) | more than 4 years ago | (#31066388)

Can you imagine the possibilities? Unleash this thing at the UN. World War III started on a google phone with the mistranslation: "It was lovely eating your daughter".

Apple will perfect it. (1, Funny)

Anonymous Coward | more than 4 years ago | (#31066434)

No doubt Google will try and fail, while Apple will try and succeed. They are just that good.

Errors (1)

Bragador (1036480) | more than 4 years ago | (#31066490)

As long as people use it to improve their understanding and not to officially communicate with others, I have no problem with that. It can be somewhat offensive to receive papers that are badly translated. If you want to communicate or sell me something, at least try to learn my language instead of faking it with computer translators. You should see the ridiculous English to French translations sometimes...

The lack of interest in learning other languages can and will lead to embarrassing situations...

http://entertainment.slashdot.org/article.pl?sid=08/08/02/2148231&from=rss [slashdot.org]

AWESOME (1)

Isarian (929683) | more than 4 years ago | (#31066524)

Google Universal Translate - Offending colleagues in their own language faster and with more energy!

Thanks for ripping me off..... (0)

Anonymous Coward | more than 4 years ago | (#31066650)

Well, this is great. This was something that I submitted to their power of 10 contest over a year ago. Seems they just used "contest" that to get good ideas to further their bottom line. My platform was the smartphones as the processor plus additional items.

"Do no Evil"..... Rolls eyes

Thanks for ripping me off Google.

Fantasy (2, Interesting)

cdrguru (88047) | more than 4 years ago | (#31066694)

The problem is primarily things like diction. You can "train" someone sitting in front of a computer to speak slowly and clearly with good diction. Fine.

The problem is the most useful use model for a cell phone translator would be getting a cab or walking into a store. You talk into your phone and it says something to the other person in their language - wonderful, because you have "trained" yourself to speak clearly and slowly with good diction.

Then the other person mumbles something back at you in their language that neither you or the cell phone can make heads or tails out of. You can't "train" them so it will never work for that.

From my limited experience, English has its share of strange accents and such but in large measure people can speak with good diction and pronounciation. Lots of non-English languages seem to promote far less clarity and human-to-human it doesn't really impair communication that much. Human-to-machine is a whole different story and we are very far away from being able to do speech recognition with poor pronounciation and poor diction.

Re:Fantasy (1)

corbettw (214229) | more than 4 years ago | (#31067022)

Then the other person mumbles something back at you in their language that neither you or the cell phone can make heads or tails out of. You can't "train" them so it will never work for that.

That's why it's important to combine this app with two others: a Taser app, and a donut-hole-dispensing app. Can't have training with punishment and reward!

Re:Fantasy (1)

Culture20 (968837) | more than 4 years ago | (#31067346)

That's why it's important to combine this app with two others: a Taser app, and a donut-hole-dispensing app. Can't have training with punishment and reward!

Is this a device intended for cops? A taser for reward, and only mere donut holes (not the whole donut) for punishment?

Limitations, sure (1)

nilbog (732352) | more than 4 years ago | (#31066740)

Sure, this has its limitations. We're not going to be conducting diplomacy with aliens on the deck of the starship enterprise using cell phone machine translation. But for simple and easy to understand things like "Where is the bathroom?" or "The cheese is old and moldy" this thing will be sufficient, I'm sure.

There is also an art to using machine translation. I don't know how to describe it, but if you input things like you'd imagine a foreigner saying them, the translation will be much better. Your input can't be the way you actually talk, it has to be more like the statements you would find in a children's book - and each thought should be contained in its own sentence.

Unearthly! (1)

Animal Farm Pig (1600047) | more than 4 years ago | (#31066756)

And often to remote areas of several speakers to visit my mother tongue. My time to learning for all the world to me. This application can really be deadly for me. I can only look at the data in small villages in Africa, when he began to speak in English and Portuguese damage my phone to imagine. I hope that the address does not require a network connection.

Collective Brainpower of Google is high (0)

gsgriffin (1195771) | more than 4 years ago | (#31067046)

There are lots of smart people here on /.

Smart people all think they are smarter than everyone else.

Google has more money than anyone here on /.

Google has already hired so many smart people (I mean REALLY SMART!!!) that if any company can make this work, it will be Google.

Let's see it happen before all of the smart people put them down. BTW...have you seen the translator on Google Wave. Its simply that with a vox.

Got NSA (4, Insightful)

dave562 (969951) | more than 4 years ago | (#31067056)

This seems like something that the NSA is probably salivating over. Imagine being able to translate intercepts in near real time with accurate voice recognition. I'm sure they already have imagined it. That technology is nothing short of a Manhattan Project for the SIGINT community.

Re:Got NSA (1)

Phrogman (80473) | more than 4 years ago | (#31067148)

And they probably started working on it a decade or two ago, and have a working version now :P

Re:Got NSA (3, Funny)

girlintraining (1395911) | more than 4 years ago | (#31067522)

And they probably started working on it a decade or two ago, and have a working version now :P

I can't confirm or deny its existance. But I can offer you one reason for the denial: The FBI. If we admitted we had it, they'd want to use it. The last time they asked for forensic analysis, it was for their cross-dressing commander who wanted to know who had shit on his front doorstep. After intensive analysis, it was determined to be a squirrel. Then they called us because they couldn't identify which squirrel. We've been hesitant to offer our services ever since. We did find the squirrel though. In another 23 years, you'll be able to submit an FOIA request for the rest of the story. Footnote 16 is especially amusing.

Some anti-snark (2, Interesting)

kroyd (29866) | more than 4 years ago | (#31067232)

It is really easy to make fun of translate.google.com based on how it translates Chinese to English. This is quite silly IMHO, as Chinese is possibly the hardest language in the world. (Travel around China and you'll find semi-literate taxi drivers, even in the major cities.[*]) This is a good article on why Chinese is hard: http://www.pinyin.info/readings/texts/moser.html [pinyin.info] .

A better example would be say Dutch. Translate the OP from English to Dutch and back to English (i.e. a worst case scenario), and you end up with this:

"The company has an automatic system for translating texts on computers, sweetened by scanning millions of multilingual websites and documents. Until now includes 52 languages, adding Haitian Creole last week. Google has a system telephone speech recognition that allows users to query websites by speaking commands into their phones instead of typing them in. Now it is working on combining the two technologies to software to understand voice of a caller and translating it into a synthetic equivalent in a foreign language to produce. "

This is perfectly legible to me, and vastly better than what you got when babelfish was introduced 11 years ago. There is a good TechTalk about the topic at http://www.youtube.com/watch?v=y_PzPDRPwlA [youtube.com] which should be required viewing before making fun of google's machine translation efforts.

Voice recognition is harder, but for continuous untrained speech recognition google voice is pretty cool - I've gotten some barely intelligible voice messages on my google voice number, and where google voice is sure (i.e. black text) it is 95%+ correct, where it is not sure it is maybe 30% correct, but for another 30% it is not possible to figure out what was said, except when taking context into consideration. Google Voice transcribing a call from a mobile phone is better than what you got with Dragon Dictate 5 years ago even with a good microphone, so it is not unlikely that in a few years it will be better than naive human transcription. Humans will be better at guessing based on context thought.

Basically, in 5 years the kind of system google is talking about will work good enough to successfully flirt with a french girl (see http://www.youtube.com/user/searchstories [youtube.com] ) :P

[*] This is why you should always bring a mobile phone, and have the number for the place you're going.

Load More Comments
Slashdot Account

Need an Account?

Forgot your password?

Don't worry, we never post anything without your permission.

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>
Sign up for Slashdot Newsletters
Create a Slashdot Account

Loading...