Google Wants Your Voice Data

00_NOP writes "Peter Norvig, Google's director of research, has told New Scientist that one of the reasons the search engine launched Google Voice is that it needs more human voice data to perfect the sort of 'big data, simple algorithm' probabilistic approach to translating voices to text that drives Google Translate. Norvig says that no one is listening to your calls on Google Voice — it is simply their servers trying to get the translation right."

Comments

Um, how

[C_Kode]

I will say that the translation of my voice mails is terrible. Although, how can you tell if it is translated correctly if you don't listen to it? You can look for proper English, but even some of my translations are proper English yet still incorrect. (names, etc come out wrong.) Though most of the time it it's just a jumbled mess that I can't deduce the actual meaning of.

Re:Um, how

[Seumas]

Your voicemails/transcriptions have a button you can check to mark whether or not it was accurate. Presumably, that is what they mean. Nobody besides *you* listens to them. On the other hand, if that is somehow not the case . . . . then . . . fuck no.

Re:Um, how

[The MAZZTer]

There is a checkmark and an X you can click if the translation is good/bad.

Re:Um, how

[PhrostyMcByte]

Although, how can you tell if it is translated correctly if you don't listen to it?

They don't listen in, at least not initially. You do. If it's not translated correctly, there's a box for you to check that gives them permission to listen.

Re:Um, how

[Anonymous Coward]

I bet their servers have all the naughty words perfected.

I agree though. Its a classic case of chicken/egg. From a innocent's perspective it makes sense. They want all voice data (dialects, accents, etc.) to improve translations not only for Google Translate but also for voice-text-voice.

In the end, do I really care who listens to my conversations? No, they can listen to all the phone sex if they want. Do I think they will be selling this data off in the future? Maybe. As long as they aren't selling my CC, address, SS#, etc, I'm good.

The days of privacy have come and are now going. Let it be. It's the cycle we should get used to now.

Re:Um, how

[kannibal_klown]

My experience with a Nexus One...

If I used voice transcribing for to the phone directly: as in I spoke to my phone to do a google search or write a text, it came out fairly well. There was the occasional error but mostly on things like names.

But my transcripts from the voice mails I receive were often trash.

I guess it has to do with the sound-quality: it probably uses the original high-quality recording locally so it performs good Google searches. Meanwhile the compression and static over the phone line (and the voice mail recording) are probably harder to transcribe.

Re:Um, how

[Anonymous Coward]

We should just get over the fact that privacy is gone, eh? Not here, my friend. Not ever. People have a RIGHT to privacy despite what anyone will tell you.

The fact that the majority of people could give a hoot in hell about their personal and our collective privacy will come back to haunt us. I don't understand why people would willingly give up their privacy for a little functionality, cool tech, gadgets, whatever. I value my privacy and I don't share my info willingly with anyone or any organization without a lawful requirement, e.g. SSN for employers, banks. I even fought my medical insurance company on getting my SSN because they have no legal mandate to possess that information.

I will not have grocery store cards to save money for the same reasons. I will not trade my personal information for a little savings.

These companies take our information from us and profit greatly while we in turn get what? A "free" email account laden with ads that track our behavior? This is not a win-win situation and no one really cares, because they can chat with their friends across the globe in real time, make "friends" on Facebook they will never meet or really know.

Where does all this end? When the entire world is one transparent collective society where no one has any privacy whatsoever? Personal information is a goldmine as is shown by how desperately companies want to get their hands on it. I think there should be a citizens' clearinghouse where people can agree to sell their info for a profit -- opt-in by default. Anyone caught trying to get around this clearinghouse pays dearly legally. Companies bid for your personal information and you profit as well. Anything short of some model like this is completely lopsided in favor of corporate interests that don't have our best interests at heart.

Re:Um, how

[Cytotoxic]

They've gotten some pretty good data from me. My Google Voice number isn't currently published, so all of the voicemails I get are wrong numbers (or tests). They are completely incomprehensible to me, and to Google Voice - although one did a fair approximation of jibberish English (I think it was in some African dialect). Most seem to be in African languages, although a few are central European sounding. Good luck getting a good translation - but that's the magic that Google is trying to accomplish: translate some spoken language without any foreknowledge. Kind of like Google Goggles only for voice. So I volunteer all of these for their translation database.

Oh, and I do get a fair number of advertizements and service calls. If you had an appointment with Comcast last Thursday, the tech called the wrong number - that's why he didn't show up. Google did a good job on the translation though...

Re:Um, how

[tophermeyer]

I've had the same experience, my voicemail transcripts are garbage.

When I speak into my phone to write a text or run a search I make a point to speak slowly and enunciate very clearly. I suspect most people don't make the same kind of effort in voicemails.

Re:Um, how

[thePig]

In that case, they can use Youtube videos for this, right? Their automatic translation is quite horrible - they could use the good/bad check there too.
Actually they can translate the same videos everytime people sees it - and until quite a high percentage of people say yes, they can test it again.
Also, when they have more than 200 Million videos in youtube, why do they need to store data from Google Voice - which is much more personal and important.

Re:Um, how

[hedwards]

If the message doesn't require a double check there's no reason for them to store it as they don't have any way of knowing whether or not it was accurate. However, for ones that they do have to go back and analyze, there's a good reason why they'd want to store them. In a word regressions. Without a body of samples which were tough, they don't have any way of gauging whether or not they're truly making progress as improvements could just as easily be in the quality of the samples that they are trying to transcribe.

Re:Um, how

[aztracker1]

What's funny is this is the case for everyone but both of my grandmothers... either one of them leave a voicemail, and it transcribes > 95% accurate, better than anyone else (30-60% usually). I guess it works well for old women raised in the U.S. midwest.

Re:Um, how

[Anonymous Coward]

Also, when they have more than 200 Million videos in youtube, why do they need to store data from Google Voice - which is much more personal and important.

Translating telephone quality voice when people are rambling and umming and ahhing and might have traffic noise in the background is very different from youtube where people are often using microphones, at least trying to speak in a clear manner, but might have music in the background.

Re:Um, how

[heypete]

Oh, and I do get a fair number of advertizements and service calls. If you had an appointment with Comcast last Thursday, the tech called the wrong number - that's why he didn't show up. Google did a good job on the translation though...

I have similar experiences, only with email instead of voicemail.

This confuses me as I've owned my own domain for just under 12 years (and was the original registrant), and am the only recipient at the entire domain. It's my personal address and a few generic role accounts (postmaster@, abuse@, etc.) that forward to my personal account. There is no reason why someone named "Diane" should use my email address (pete@[my slashdot username].com) when scheduling an Apple Store appointment in South Carolina (not a state where I've ever lived).

Yet, oddly enough, it happened on April 11th of this year. Go figure.

Re:Um, how

[darkshadow88]

That is absolutely correct. Speech recognition is incredibly sensitive to sound quality and background noise. When you're talking into your phone, the ASR software has a very good quality sample to work with. On the phone line, however, you're dealing with a very noisy signal, which causes huge degradations in the quality of recognition.

Re:Um, how

[SETIGuy]

In the end, do I really care who listens to my conversations? No, they can listen to all the phone sex if they want.

They aren't listening to your conversations. They are listening to your voicemail if you send it to them. And if someone were to have phone sex with my voicemail, whether I sent it to them would depend upon who was calling.

Re:Um, how

[davester666]

No"BODY" is listening, but computers are analyzing every call and transcribing it to text?

Hmm, I would guess there would need to be at least some spot-checks that the transcription is working properly.

And isn't there some kind of federal wiretapping law preventing this or is it a "well, we told you we were listening in on every call"?

And methinks it just might be easier for the gov't to get these transcriptions instead of the actual audio recordings. And more convenient to, because it's much faster to read/search them instead of listening to hours and hours of audio.

Re:Um, how

[Anonymous Coward]

And if you hit "No" saying the translation was not effective Google allows you to submit the voicemail to them for someone to listen to. I submit all of my bad voicemails to them, so they DO listen to voicemails, but only if you give you them explicit permission for particular voicemail.

Re:Um, how

[NeutronCowboy]

You assume that privacy has value. What value really is there to it? There are a few good examples, but none of them apply to the current scenario, or even the sharing of email addresses. And before you reply "Because", think about the value judgment that you're making. What exactly is it that makes privacy as valuable a concept as, say, equality or liberty?

Finally, a free email system of the quality of gmail is worth a lot to me. Google can have the privacy that they're asking for it. One thing is sure though: as much as I'm ok to trade my privacy for a free email account like gmail, they better ask me for it. Switch-and-baits and fine print or outright lying is grounds for immediate blackballing of the company.

Re:Um, how

[RanCossack]

No"BODY" is listening, but computers are analyzing every call and transcribing it to text?

Hmm, I would guess there would need to be at least some spot-checks that the transcription is working properly.

You do, when you click the check-mark or the red X after listening to it. However, that is a good point -- here Google says nobody will listen to your voicemail, but they still let you listen to it. So much for don't be evil! (This is sarcasm.)

As for other people getting ahold of the transcriptions... not to be too facetious, but given how bad the quality currently is, nobody should worry about that yet. ;)

Re:Um, how

[Anonymous Coward]

If you have enough voice data, even if very little of it is actually manually transcribed, you can still improve the accuracy of a translation system. It just involves a lot of math that I have neither the time, intelligence, or patience to bother understanding.

Re:Um, how

[LunaticTippy]

Maybe they use a land line. I've noticed my friends who use land lines (small sample size) have high accuracy rates relative to average.

Re:Um, how

[Anonymous Coward]

My privacy is mine and therefore valuable to me. Human being aspire most to freedom. Freedom in this context is controlling who has access to information about me and my life. My comings and goings in public are exactly that -- public. My non-interactive dealings online are my own business, unless I agree to share them with other people. Opt-in is the byword, not opt-out.

As a default rule, I filter out all ads, all cookies, and all tracking info that could potentially invade my privacy. My webmail doesn't require cookies to be set. I'm not paranoid, just careful. I've been in the IT industry for well over a decade and in IT security for a goodly portion of that time. I know what goes on in the background.

Just as an aside for people interested in security... there are some cookies that are not cleared out when you flush your cache and cookies. These are known as LSOs -- local shared objects -- Flash cookies. They are used to track you and follow where you surf. You can have Flash functionality but not save these cookies to disk by simply blackholing these cookies to /dev/null

If you are a Windows (or Linux, too) user and use Firefox, you can get the Better Privacy add-on, but with Linux it's better to just blackhole the cookies, as nothing escapes the even horizon of /dev/null.

Linux How-To

cd $HOME
rm -rf .adobe .macromedia
ln -s /dev/null .adobe
ln -s /dev/null .macromedia

Enjoy Flash with no cookies being set...

Also check out Better Privacy and Ghostery. Sites can also use CSS to track you by your visited links. To prevent this, have Firefox always start in private mode or set remembered URLs to 0 (zero).

Enjoy...

Re:Um, how

[yakatz]

Your voicemails/transcriptions have a button you can check to mark whether or not it was accurate.

And once you click that button, you have the option to donate your message so they can use it to improve their software. Example: http://img808.imageshack.us/img808/242/unled90.png

Re:Um, how

[yakatz]

And if you hit "Yes" saying the translation was effective Google allows you to submit the voicemail to them for someone to listen to. I submit all of my not-important voicemails to them.

Re:Um, how

[RoFLKOPTr]

Hmm, I would guess there would need to be at least some spot-checks that the transcription is working properly.

The only time somebody at Google listens (well, is allowed to listen) to your voicemail or recordings is when you click the red X and consent to their review.

Re:Um, how

[davester666]

Well, wouldn't it be worse if the transcription was wrong and the SWAT team comes to your house because they think you are making a bomb instead of just noting that the movie bombed...

Self-checking

[rwv]

How do servers assess whether they've got the translation correct without having a human-in-the-loop to listen to the conversation and concurrently read what the server translated? Maybe the data is anonymous by the time it gets to a human, but it seems like humans need to interface with the voice data somehow to validate that the server is translating accurately.

Re:Self-checking

[msauve]

"How do servers assess whether they've got the translation correct without having a human-in-the-loop to listen to the conversation and concurrently read what the server translated?"

If you log into your Google Voice page, and look at a translated message, in the lower right corner there is the question - "Transcript useful?" along with yes/no checkboxes. If you check one, it asks if you want to "donate" that VM to improve the translations, you can answer yes/no/never:

Want to help Google's automated transcription get better? Donated voicemails will be listened to, manually transcribed, and used to improve our transcribing server's accuracy. They are only used for this purpose.

Re:Self-checking

[Anonymous Coward]

It's the Google Voice user that does the correction of Google's transcriptions. When one receives the transcription, Google asks if they got it correct.

Re:Self-checking

[alostpacket]

You are the human in the loop. If you read the VM from the website you have an option to submit the recording if the translation wasn't helpful.

Re:Self-checking

[mrchaotica]

It's too bad they don't let you fix the transcription. Even if they're worried about people trying to poison their data (like people talk about with ReCaptcha), they could at least the user fix his own view of it.

Re:Self-checking

[gnapster]

Or they could just give it a once-over to make sure it's okay. I mean, someone is already taking the time to listen to the voicemail and re-transcribe it manually. It would take less time to verify that the user-generated transcription is correct.

Re:Self-checking

[Anonymous Coward]

Easy - they have a service which re-translates the text back into the original speech. If both the re-translated version and the original version match, they know the in-the-middle translation was accurate.

Re:Self-checking

[QuantumRiff]

I don't understand why they don't let me correct it myself.. Not only would I be helping them with their algorithm, but then I would have a known good transcript to save in my voicemail for later searching.. (Searching is pretty bad if your looking for a word or phrase that is often mis-interpreted).

Re:Self-checking

[coolmadsi]

I don't understand why they don't let me correct it myself.. Not only would I be helping them with their algorithm, but then I would have a known good transcript to save in my voicemail for later searching.. (Searching is pretty bad if your looking for a word or phrase that is often mis-interpreted).

I suspect the fear of trolls mistranslating is too great to allow anyone to do it.

Imagine some people "helping" the algorithm by insisting that if someone says, say, "music" it actually "translates" to "we're no strangers to love".

nice

[Anonymous Coward]

>simply their servers trying to the translation right
>trying to the translation right
>the translation right

Nicely done.

Re:nice

[alostpacket]

Apparently they're already on par with your average Slashdot editor.

Re:nice

[Anonymous Coward]

Yeah, yeah, they accidentally the whole word.

Re:nice

[RussellSHarris]

Think of the translations, man... they have rights.

Re:nice

[Anonymous Coward]

Slashdotters can't greentext.

Re:nice

[martin-boundary]

Apparently they're already on par with your average Slashdot editor.

Google voiceover: Gentlemen, we can rebuild CmdrTaco. We have the technology. We have the capability to build the world's first bionic slashdot editor. CmdrTaco will be that editor. Better than he was. Better... stronger... faster.

Re:Huh?

[Anonymous Coward]

First post? Tell it to google, I'm sure they'll listen.

servers trying to the translation

[foma84]

oh shit! Google accidentally my voice data!

Re:servers trying to the translation

[m0rphin3]

Once, I accidentally my voice data, but then the Google server so it was OK.

Re:servers trying to the translation

[dzfoo]

I what you did there.

Re:servers trying to the translation

[Anonymous Coward]

Is that where that stupid meme came from? A bad Google Voice transcription?

Suddenly it makes a lot more sense.

They Make it Hard to Delete History

[Quantum_Infinity]

I can tell that they want the voice data badly. They make it very difficult to delete call and voicemail history. You can't delete more than 10 records at a time and even then they go into trash and keep piling up over there. You can delete the data from trash but again only 10 at a time. There is no option to empty the trash. Their help section says that the history is purged from trash after 30 days automatically but only that it isn't. My call history sits in the trash indefinitely unless I painstakingly delete all history 10 records at a time.

Re:They Make it Hard to Delete History

[_0xd0ad]

Good news - after you go through all the painstaking, tedious work of deleting them ten at a time, they're really gone forever!

*snort* yeah, I couldn't keep a straight face while typing that. Hopefully you couldn't keep one while reading it, either.

Re:They Make it Hard to Delete History

[Anonymous Coward]

Not only that, they've made it impossible to flag whether or not a translation was any good from mobile devices - both Android-based and Blackberries are lacking this feature inside the Google Voice program. The only choice is to go online, log in, and do it. That's an extra step, and most people aren't going to go out of their way to do that.

Google, are you listening?

Re:They Make it Hard to Delete History

[martin-boundary]

Sounds like somebody should write a 'droid app to fix that...

Error in summary

[Anonymous Coward]

"it is simply their servers trying to the translation right"?

Slashdot accidentally the whole verb!

Or maybe they just put it through Google Translate... it's 'probably' right.

biometric id

[Anonymous Coward]

My voice is my passport. Verify me.

Google Wants Your Voice, Data

[Anonymous Coward]

Brent Spiner would want to be paid for it.

Another server

[KingSkippus]

They have another server that checks the first server's translation. Part of their work is checking that server's affectiveness, too.

Is anyone surprised?

[bravecanadian]

This is the price of "free" services.

Re:Is anyone surprised?

[afex]

no, we're not - and I will GLADLY pay this price, if not more. If you are a GV user, then you understand how insanely valuable the service is.

on the flipside, if you're a privacy advocate (which I absolutely get!), then don't sign up.

the thing that I don't get is people shouting "i told you so" at all the people that use google services - we get it, we already know they want to mine our data - and we WANT to give it to them!

*disclaimer: i do not use GV due to the fact that I MMS more than a teenage girl - but I do look at the others that use it with envy : (

Re:Is anyone surprised?

[Anonymous Coward]

If you're a privacy advocate, don't answer 'yes', when you're asked if you want someone at Google to listen to your message.

Re:Is anyone surprised?

[TaoPhoenix]

We are derisive towards "Hai This is Facebook. Plz give us ur full name, address, cell phone number, age, and eye color so we can give you five Farmville sheep."

But you bring up the more interesting case, "Awesome service versus abused data". (Shout out to Holland and TomTom for yesterday's example.)

Or here, Google Translate vs ... a billion hours of juicy phone calls!

Speech is "Audio" - All we need is a hacker and a Wikileaks Dump!

Re:Is anyone surprised?

[Krishnoid]

This is the price of "free" services.

on the flipside, if you're a privacy advocate (which I absolutely get!), then don't sign up.

And sometimes you pay the price anyway, without your consent, and when the services aren't "free". Given the (lack of) choice of my data and money going to a company that isn't really innovating that much, or to an entity that's ostensibly trying to move the state of the art forward and using data at least partially to this end, I can't see how a privacy advocate would consider GV worse than their current voice service.

A "false-sense-of-privacy advocate", perhaps, or one who refuses phone or voicemail service entirely on these grounds.

Re:Is anyone surprised?

[gnapster]

I use a typewriter to hand-transcribe my answering machine messages from cassette tape, you insensitive clod!

I gave up

[dargaud]

I gave up trying to get voice software to work over a decade ago. The reason is that I'm trilingual and use all 3 daily. So the software needs to be able to:
- understand a lousy accent: there are some words I cannot and will never be able to pronounce 'right'
- recognize what language is being spoken (having those 3 and only those 3 preset in the options)
Now I haven't tried Google Voice, but none of the software I've tried or heard about could even remotely do those two basic things.

Re:I gave up

[Thavilden]

Those two requirements don't exactly strike me as "basic".

Re:I gave up

[hedwards]

Considering that outside of Africa only a very small fraction of the population speaks more than two languages let alone fluently, I don't think that it's a basic request.

Re:I gave up

[Cytotoxic]

Google Voice is pretty amazing, even at the early stages. It can auto-recognize many languages. It can also do a fair job with bad pronunciation. Google translate is able to understand my Spanish - which is fairly incomprehensible. Of course, my vocabulary is limited to that provided by public high schools in rural North Carolina back in 1982. Good luck getting me to do more than ask for directions to the bath room.

I'll steal a joke from David Sedaris - a single year of high school Spanish just isn't enough to function in society. Trying to borrow a lighter walking around Mexico City I had to go up to people and ask to borrow some fire: podría darme un poco de fuego?

That didn't really happen - it was Sedaris talking about his adventures in France. But it could have been me. In my case it was rural Mexico on the Yuccatan looking for some Hydrocortisone ointment for the wife (who was getting eaten alive by mosquitoes). You try explaining allergic reaction to a 14 year old Mayan girl manning a pharmacy in rural Mexico while using the vocabulary of a 3 year old.... good luck sounding like anything more than an idiot. I finally had to write down "hydrocortisone ointment, 1%" on a piece of paper. She produced a tube of 2.5% ointment (prescription strength in the US - woot!) and earned my wife's undying gratitude. I can only imagine how easy that transaction would have been with google translate. Heck, if I just knew the words for "skin" and "bite" at the time it would have been really helpful...

Re:I gave up

[camperdave]

Considering that outside of Africa only a very small fraction of the population speaks more than two languages let alone fluently, I don't think that it's a basic request.

It strikes me that Europe might disagree with you on that.

Re:I gave up

[the_fat_kid]

I used to work with a "trilingual" fella.
Born in Itally, raised in France, and then lived in the USA for 17+ years.
He effectively spoke no language.
Bad Itallian, worse French and jumbled English.
is there an app for that?

Re:I gave up

[icebraining]

I don't know, even in Spain where they have a dozen languages, few people speak three of them (or two + English).

Re:I gave up

[Anonymous Coward]

And India, a country one-third the size of the US and four times the population, with 22 official languages, 415 languages and more than a thousand dialects.

Re:I gave up

[Anonymous Coward]

Or Asia. Or South America. Or anywhere...

Re:I gave up

[Anonymous Coward]

They are basic (in the sense that they are a must) for a tool like google voice's.

To tell apart different languages and guess when a word is a foreign language word.
I know three languages. Mother language (spanish) second language (english) and some japanese.
I can still tell when somebody is speaking different languages that I barely know(german, french, chinese, portuguese, italian).

To put into letters words that it does not have in its vocabulary and no just try and find the closest match

To understand different accents.

Re:I gave up

[SydShamino]

The Malaysians I know do. They all speak a local dialect (their first language), plus they speak Mandarin (the regional language taught for normal communication), plus they speak English (the language they learn to conduct business). They can't really co-mingle the applications, either; they don't know many business terms in their native language so English isn't just an option, it's preferred for those uses.

Re:I gave up

[hedwards]

I could be wrong, but I doubt most Europeans are fluent in more than two languages, and I bet a significant number aren't fluent in multiple languages. The reason I'm singling out Africa there is that in parts it's very common for people to speak not just one or two, but three, four or more languages and to have to learn a new language at marriage so that they can communicate.

Trust me, Europeans have nothing on that.

Re:I gave up

[_0xd0ad]

have to learn a new language at marriage so that they can communicate.

Married people communicate?

Re:I gave up

[Abreu]

Va te faire enculer, pendejo

Re:I gave up

[Abreu]

I have had "conversations" with people coming back to Mexico after living years in the US... poor fellows, their Spanish is incomprehensible and their English sounds like a racist joke.

Pochos have really developed their own pidgin language :S

Re:I gave up

[xaxa]

Considering that outside of Africa only a very small fraction of the population speaks more than two languages let alone fluently, I don't think that it's a basic request.

40% of EUropeans speak English well enough to have a conversation (not including native speakers). In some areas (Switzerland, Belgium, Luxembourg, places near country borders) it's not unusual to speak an extra language.

If you're a European child you speak [your version of European], learn English at school because English is useful, and if you like languages you might choose another; in the same way, perhaps, that an American child might choose to learn Spanish.

I know a little French and a little German -- nowhere near enough to have a proper conversation (I'm still learning) but enough that if I see some French or German text I try and understand it before hitting the "Translate" button. I'm also by far the least multi-lingual in my house, the other three people are fluent in either two, three or four languages.

Re:I gave up

[xaxa]

One of my flatmates speaks four languages fluently. I think her English is at least as good as mine was when I was 16, in some cases better (consistently using "whom", "and I" etc correctly).

I'm learning German; when I get a little better I want to have German-speaking Sundays (Deutsche sprechen Sonntags?... Wrong conjugation of sprechen, probably the wrong word order, oh well, I've not been learning long.).

Re:I gave up

[darkshadow88]

"Deutschsprechende" is probably what you're looking for.

Re:I gave up

[Ksevio]

You might have more luck with software that has a training phase before doing recognition. I've had great success with Germans, Chinese and Israelis speaking English through extra training.

As for the language, I'm not sure about consumer software, but phone systems (and probably Google Voice...details are slim on it) will often run recognizers for several languages and then go with the recognition with the highest confidence.

Re:I gave up

[jodio]

I'm Canadian and I speak 3 languages. English, French, and Rubbish. Mostly Rubbish.

Re:I gave up

[Confusador]

Funny, I was just thinking that everyone has to learn a new language to communicate after they get married.

Re:I gave up

[fritish]

I haven't heard the Sedaris bit, but in France you can actually ask for "fire" when you want a "light". "Can I get a light?" -> "Tu as du feu?" (I do get your point though.)

But even ignoring that you can ask for "fire" in France, auto-translators have to realize that you can't word-for-word translate, but also understand that written language is often different than spoken language. Some have started to pick up on this, but they all still have a ways to go.

Re:I gave up

[tdknox]

My fiancee speaks 6 languages fluently, like a native, and switches between them with an ease that impresses the shit out of me. They are Korean (she is Korean), Tagalog, Mandarin Chinese, English, Japanese and French. The first time she came to America, Immigration didn't want to let her in because her English was so good they didn't believe that she had never been here before.

So, yeah, there are lots of people that speak multiple languages. Just not, unfortunately, in America.

Maybe it tried to translate the summary

[Bob the Super Hamste]

Maybe google voice tried to translate the summary:

it is simply their servers trying to the translation right.

Re:Maybe it tried to translate the summary

[Attila Dimedici]

Hey, that would be useful, a service that translates slashdot summaries into English.

Re:Maybe it tried to translate the summary

[snspdaarf]

By the time the servers are that powerful, they could run Crysis.

Re:Maybe it tried to translate the summary

[berashith]

no, it would look more like this ...

innocent lythe airs her versed rhyme to theatre and slay shun, right?

Yeah, you need voice data to get voice to text

[sjvn]

And you're surprised why? All voice apps. do this. Always have, always will, and until it's perfected, and we're a long, long way from perfecting it.

Steven

Hmmmmm, looking for accuracy are we?

[achenaar]

"it is simply their servers trying to the translation right"
I think you a word in your sentence.

Doesn't work well...

[sglewis100]

"Peter Norvig, Google's director of research, has told New Scientist that one of the reasons the search engine launched Google Voice is that it needs more human voice data to perfect the sort of 'big data, simple algorithm' probabilistic approach to translating voices to text that drives Google Translate. Norvig says that no one is listening to your calls on Google Voice — it is simply their servers trying to the translation right."

I think Google Voice translated the last part of that sentence.

Entertaining anyway

[Anonymous Coward]

The translation is off pretty far most of the time for my voicemail. But they do end up to be entertaining. Here are two actual translations from google voice:

1) Okay, I don't know why it takes for ever, for your voicemail to pick up. But anyway, I was just calling to tell you that we forgot to while. I will and I told Mrs. Smith and this is best but she signed about it, so I'm gonna shout in the car and have it for her after I pick her up, bye. You Get Out virtual slot is not with us. So, wish me luck. I don't have to run out over there, bye.

2) Hey, it's me. Yeah, I would you like. The has the can't seeing tomorrow night and then there's the car was up for a late night should keep talking about it I'm sure wondering if we could let him get the cantinas left for due to Cardiff blues. I thought I'd run it by you and see what you thought, let me know if any a message or something, so I can out and I will talk to you later. Bye.

Re:Entertaining anyway

[Anonymous Coward]

You think thats bad? Try

Hello hello, hey hello. Hello. Okay bye. Hello, bye bye. It's okay. Hello. Bye, okay. HI hey. I was okay bye. Hello, work hello, bye bye hey. Hello. Hello. Hello, ohh bye bye. Hello. Bye, couple hello, cos hello. Bye bye hello. Hello. Hey.

I is have hamburger?

[ook_boo]

Right. Everyone get on Google Voice with funny unnatural accents, unusual intonation and non-native grammar! Let's skew their data.

Re:I is have hamburger?

[Anonymous Coward]

Epic wonderment! I'm get near to this.

Re:I is have hamburger?

[Anonymous Coward]

Open it up to Canada and i'm sure it'll get pretty fucked pretty quick from here in Newfoundland. :)

Re:I is have hamburger?

[delinear]

Let's speak MS at it...

Dear aunt, let's set so double the killer delete select all.

Comment removed

[account_deleted]

Comment removed based on user account deletion

the whole truth, accept no substitute, alternative

[Anonymous Coward]

as far as conspiratorial fear mongering? who does it better? the truth. other outstanding features; religious crusaderism, chosen ones minionisms, genocidal historisms, & restorisms. then there's mythical magical fictional being promotions, & real sex religious 'trainings'. who do we trust? thanks again for the observable progress by others in the disarming arena. as for the 'weather'? tell the truth.

Re:Huh?

[Anonymous Coward]

Except of course the servers, and the people later on who are looking at the translation and also listening to the original perhaps to see if it was correct.

Yes, if you agree to them doing it.

Which means you're a moron for not knowing what you're talking about.

Oblig. UserFriendly comic

[JSBiff]

There was a Userfriendly.org strip years ago which pretty much summarizes my experience with voice recognition software for the past 15 years. . .

I can't find the link to the comic anymore, but basically, one of the guys in the office had been trying to use voice recog software. Some of his coworkers come to his office. He's not there, but on the screen, they wonder about the mysterious message, "Cod Am Pizza Ship".

Same reason...

[Anonymous Coward]

I think I read somewhere that this was the same reason that Google 411 launched. It was a great, free service for getting directory information from a cell phone or home phone. What Google was really doing was collecting and testing voice recognition algorithms.

Unfortunately, they killed the service last year. Now I use a free one sponsored by Bing. Go figure.

Just found it. . .

[JSBiff]

The Strip.

Re:Just found it. . .

[Rolgar]

The Ubersoft comic ran a Google Voice comic of similar humor today.

Note: The characters are running from Apple zealots, while working on a special project to prevent Steve Job's ego from destroying everything.

Google being sneaky here?

[Anonymous Coward]

Check out the app Communicate for Android - it grabs every word nearly spot on.

Oddly enough, if you use Google Voice Search and opt-out of the 'personalization' feature that records your voice and stores that data with your account - it doesn't work anywhere nearly as well.

What is going on? How can this app, built on Google Voice, be so accurate, while the companies native offering doesn't fare as well unless you 'teach it?'

Tinfoil hat says the company is mis-hearing your voice on purpose, to encourage you to upload your voice samples, which fits nicely in the grand scheme of things.

Re:Google being sneaky here?

[darkshadow88]

There are many ways to do speech recognition, but one thing they all rely on is training. My guess is that you have a reasonably "average" sounding voice, and therefore the training that was done on other people's voices (specifically, the other users of the app you mention) works well enough for you. For someone with a substantially different sounding voice, it would probably work far worse than Google Voice.

I should also point out that checkbox or no, the app you're using certainly is training. It may not be telling you that it is, but with every utterance you make, it most likely is. If it's not, then it trained on someone else's speech and you just got lucky that it works. That's how speech recognition works, and if you don't believe me, I can direct you to a number of papers on the topic.

Dang!

[PPH]

Y'all kin have mah voce data. Sheeeit! I warn't doin' nutin' wid it anyhows.

Re:Dang!

[Anonymous Coward]

Ah'm waitin' fer them ta pay real caysh money fer mah voice dayters!

Re:Dang!

[PPH]

Stand by. We've got an incoming call from King George VI.

Go ahead. Mod me -1 Insensitive Clod.

Google needs to improve their algorithms

[Anonymous Coward]

so they can send higher quality data to the CIA / NSA about what you are saying and who you are saying it to.

If we get the heuristics back as FOSS

[cyrus0101]

I'd be willing to let this happen if google then released the derived heuristics as free open source software. I'll share if you share.

Posting this from google voice

[hardaker]

Google is knot an evil umpire. They our hear 2 us with wheel whirled problems. Please stop bash tag google. All your words belong to us.

Google Wonders, "How Can We Become MORE Evil?"

[RobotRunAmok]

Google announces Google Voice, noting that it will be archiving and auto-transcribing subscribers phonecalls.

"But don't worry," Google Voice Product Evangelist Boris Badinov said at the press conference announcing the service's launch. "We promise full interoperability with Google Docs, GMail, Android, and the NSA. Also, the artist who does the daily search engine doodle has promised to come up with a really cool, shiny logo."

And around the world, geeks sign up in droves, many noting that they didn't even realize they needed this, but if Google sez it will be shiny, they'd better get on board with it quickly.

Re:Google Wonders, "How Can We Become MORE Evil?"

[Anonymous Coward]

At least they're not apple.

Who on top of doing all that evil. Would also charge you $ for it. And then sue you if you didn't bend over fast enough.

Google is breaking wiretapping laws everywhere

[Anonymous Coward]

It's interesting that all the comments so far have been about the technology etc.

This breaks just about every federal and state wiretapping law that exists. If a person or organization wishes to record the phone conversation of two individuals, according to federal law, one party must have full knowledge that the call will be recorded and give her consent before the call.

Additionally, according to some states' law, both parties must have full knowledge and give prior consent.

The key here is the prior consent. Google is breaking all of these laws by recording first then telling the people after the call about it. By that time the recording is a criminal act, no matter what under federal laws and ALL state laws.

Re:Google is breaking wiretapping laws everywhere

[utkonos]

In Virginia: "Virginia's wiretapping law is a "one-party consent" law. Virginia makes it a crime to intercept or record any "wire, oral, or electronic communication" unless one party to the conversation consents. Virginia Code 19.2-62. Therefore, if you operate in Virginia, you may record a conversation or phone call if you are a party to the conversation or you get permission from one party to the conversation in advance. That said, if you intend to record conversations involving people located in more than one state, you should play it safe and get the consent of all parties." Google is breaking the law because they are not informing both parties of the recording in advance. I'm sure that all this information is buried somewhere in the terms of service that you click "yes" to without reading it. But, unfortunately for google, that does not satisfy informed consent laws. Some states even require consent on a call by call basis, so blanket consent is automatically invalid and illegal.

Re:Google is breaking wiretapping laws everywhere

[calderra]

$2 says your "consent" is buried in the TOS.

Re:Google is breaking wiretapping laws everywhere

[udoschuermann]

Are you sure that signing up for Google Voice doesn't include a clause giving them permission to store the audio? IANAL, but I would also presume that they could successfully claim that it is obvious that a voice mail service must record the audio in order to store and reproduce it later.

Re:Google is breaking wiretapping laws everywhere

[Anonymous Coward]

Uh, it's a voicemail service and presents itself as such. Intention to record is kinda implicit... 'cause, you know, that's what voicemail is. Besides which, it also warns parties explicitly. It's called a "greeting".

Re:Google is breaking wiretapping laws everywhere

[_0xd0ad]

It'd be kind of hard to leave a voice mail if you didn't want the receiving party to record it. Implied consent much?

Re:Google is breaking wiretapping laws everywhere

[Anonymous Coward]

This breaks just about every federal and state wiretapping law that exists. If a person or organization wishes to record the phone conversation of two individuals, according to federal law, one party must have full knowledge that the call will be recorded and give her consent before the call.

WTF are you talking about? This is about transcribing voice mail messages. What idiot leaves a voicemail message without realizing it is being recorded? And certainly the owner of the account knows it has voicemail. There are your 2 parties, so where's the violation?

Google voice also allows you to record portions of a regular phone conversation, but as I recall, it announces when it is turned on and off, and it won't let you turn it on for a call that you place (presumably to prevent the scenario where you place a call and then turn on recording before the other party has an human join the conversation).

Re:Google is breaking wiretapping laws everywhere

[Anonymous Coward]

You don't seem to understand what Google Voice is. They're not recording your calls, just your voicemail. If you're under the impression that recording voicemail is "a criminal act", then you must have some really creative designs for a voicemail service...
 
...or you're just a moron.

Re:Google is breaking wiretapping laws everywhere

[amRadioHed]

Do you not understand what voicemail is? How can record a message for someone without consenting to it being recorded?

Re:Google is breaking wiretapping laws everywhere

[Lunix Nutcase]

Sure for the person owning the phone, but that hardly is going to provide consent for the person calling you in states that require 2 party consent.

Time for more testing

[empty_other]

So.. They are trying to teach GALaDOS (Google Artificial Lifeform and Disk Operative System) to speak?

Algorithm focused services

[CODiNE]

This is the same as how they put "Closed Captions" on youtube videos.

Google has no interest in crowd-sourcing the translation or transcription of speech, they want it all automated.

Which is why YouTube Closed Captions SUCK!

Voluntary

[drb226]

GV has had an opt-in feature to basically donate each GV transcription to Google with an indicator of whether you thought it was a good or bad transcription. Is there any evidence that Google is delving into your voice data without your consent? Were you expecting a GV transcription *without* a machine at least analyzing the voice data that came in and then discarding it?

YouTube

[geoffrobinson]

Just grab audio from thousands of dialogs or talks on YouTube and test it out.

EzScramble[tm]

[Anonymous Coward]

Play talk radio or music in the background. Loop recital of you saying alphabet. Baby crying. etc.

Voice OS

[Deliveranc3]

There will only be one voice operating System. Google wants to get there first.

Is voice signature what they really want ?

[tchi.keufte]

I'm sure Google wants to be able to identify people by their voices... I mean in the digital era, where you have pseudonyms, multiple identities, and where portable (micro)phones are proliferating, it would be a mistake not to take advantage of the opportunity to identify or disambiguate people's identity thanks to their voice signature... I'm going to choose my future phone operating systems very carefully...

amazing translation i got yesterday

[nathanbeach]

I love the idea of the feature -- I hate stopping to listen to voice mails. ...but I got the most ludicrous / hilarious translation yesterday. Pure poetry!

"Hi, My name is The bring the Anderson and I was interested in ordering. I'll call. Sarah, Mrs. Kate, on the Hudson birthday. He really liked all here in the for you. So, anyway, I would see it for next Sunday. I'm not sure where they said of. It's Hey Lady, Thank tonight anyway. If you can just give me a back. My phone number is 972."

Good to know about the "helpful? / donate" feature (from a comment above), which I did for this one...

Uh Huh....

[Anonymous Coward]

"Norvig says that no one is listening to your calls on Google Voice — it is simply their servers trying to the translation right."

Uh Huh... Suuuuuuuuuuuurrrrrrre they are.

big data, "good" algorithm

[Anonymous Coward]

Those two requirements don't exactly strike me as "basic".

Computers do things far from "basic" with a good algorithm.

Now how did the machines know

[Anonymous Coward]

"Now how did the machines know what Tasty Wheat tasted like, huh? Maybe they got it wrong. Maybe what I think Tasty Wheat tasted like actually tasted like, uh ... oatmeal or tuna fish. That makes you wonder about a lot of things. You take chicken for example. Maybe they couldn't tell what to make chicken taste like which is why chicken tastes like everything!"

Echelon

[Anonymous Coward]

$20 says the CIA outsources Echelon to Google in the near future.

All I can say is

[Anonymous Coward]

FAIL. They can not win. I posted this way for more than one reason. Why the lag on the text box eh?Fail on slashdot too.