Slashdot is powered by your submissions, so send in your scoop

 



Forgot your password?
typodupeerror
×
Iphone Communications The Internet Apple Technology

Apple's Siri May Soon Process Voice Locally On a Device, No Cloud Required (appleinsider.com) 83

Proudrooster writes: "Apple wants Siri to become more useful to users when not connected to the internet, including the possibility of an offline mode that does not rely on a backend server to assist with voice recognition or performing the required task, one that would be entirely performed on the user's device," reports Apple Insider. Just give it 10 years and everything old is new again. Siri will join the ranks of Ford/Microsoft Sync and Intel Edison. Do any other phones/cars/speakers have this option right now? The new capabilities are outlined in a recently-published patent application that describes an "Offline personal assistant."

"Rather than connected to Apple's servers, the filing suggests the speech-to-text processing and validation could happen on the device itself," reports Apple Insider. "On hearing the user make a request, the device in question will be capable of determining the task via onboard natural language processing, working out if the requested task as it hears it is useful, then performing it. "
This discussion has been archived. No new comments can be posted.

Apple's Siri May Soon Process Voice Locally On a Device, No Cloud Required

Comments Filter:
  • French toast, m'ladies

    (tips toque seductively)

  • by Anonymous Coward

    Welcome to 1998: https://en.wikipedia.org/wiki/Microsoft_Speech_API#SAPI_4

    • Why the sarcasm? (Score:5, Insightful)

      by SuperKendall ( 25149 ) on Saturday November 17, 2018 @04:39PM (#57661502)

      20 years from desktop to pocket sounds pretty impressive to me!!

      And frankly it will probably work better than the old desktop stuff did which moistly did not take off (though Dragon seems to have done well with desktop software).

      • by TWX ( 665546 )

        Not really. The desktop computers doing it were 16MHz Macintosh LCII models with 4MB RAM. I remember playing with Dragon in 1992 when in school.

        • You looked pretty silly carrying that Macintosh with you as you walked down the street, though - doubly so with that ginormous extension cord.

        • The desktop computers doing it were 16MHz Macintosh LCII models with 4MB RAM

          Let me check... nope still cool to have desktop software moved into mobile, even I the mobile processor is more advanced.

          I have to think the stuff moving into mobile is a lot more accurate and can handle way more accents/languages than that ancient software though, so it's not like there has been no advancement that makes use of improved hardware.

      • 20 years from desktop to pocket sounds pretty impressive to me!!

        Epic troll, dude. The first friggin' iPhone 10+ years ago had more processing power than a typical 1990s desktop. +5 insightful indeed.

    • by Anonymous Coward

      ROFL.

      True story: 20 years ago I bought via voice for my family. This new amazing product looked very impressive and promised to take the pain out of typing for family members who had "hunt and peck" typing methods.

      The result: utter crap. It couldn't get anything right, so you spend the same amount of time copyediting the gibberish it had transcribed as you would have hunt-and-peck typing it.

      The technology 20 years ago doesn't compare to modern results (which is really just the associated processing power be

      • 25-year-old dictation software did indeed suck. But the voice-control software worked well enough (PlainTalk, nee MacInTalk, did, anyway). Frankly, the voice-recognition software in my Echo seems roughly comparable to what Apple was doing 25 years ago, which is more depressing than anything else.

  • by jfdavis668 ( 1414919 ) on Saturday November 17, 2018 @04:35PM (#57661494)
    Sorry, I didn't get that...
  • by TWX ( 665546 ) on Saturday November 17, 2018 @04:50PM (#57661542)

    This really shouldn't be patentable. We had the ability to control computers with voice a quarter-century ago. Not only would there have been patents back then, but those patents would have expired long ago.

    • >"This really shouldn't be patentable."

      Exactly. I was wondering the same thing when I read the summary. Voice recognition on a "X" isn't really any different than on a "Y" or "Z". Now, if the *methodology* they are using is considerably different/improved, I would think THAT could be patentable, but not simply that a phone can perform voice recognition. Otherwise, it is a matter for copyright.

      Software patents are horribly abused. Ultimately, consumers are always who suffer due to higher prices, fewe

      • by rtb61 ( 674572 )

        There is a patent in there, you just don't realise it. As a person device, it is no longer blanker voice recognition, but you recognition, it recognises your acoustic contact and learns to adapt functions to it. Technically you should be able to include whistles or any other noise generation technique to teach the device to adapt to you, with your voice as being the basic acoustic control engine. Of course taking your voice off the internet, making it private between the device you own and yourself means, A

    • by swell ( 195815 )

      More specifically: "Offline personal assistant." ...

      is 90% identical to "Online personal assistant", and obvious to anyone familiar with the industry.
      There is nothing novel in this technology.

      And yes, I agree, most modern patents are obvious to anyone in the industry.
      And that fact is obvious to the patent examiners, yet they are approved.
      Very frustrating!

    • You don't understand this is new. It's like the original idea, but on a computer. ... errr in a pocket.

  • Android Assistant... (Score:4, Informative)

    by Tomahawk ( 1343 ) on Saturday November 17, 2018 @05:02PM (#57661578) Homepage

    ... can perform some tasks offline. I can send an email, navigate, and change phone settings (adjust volume, etc), probably more. I've tested these in aeroplane mode and they worked fine.

    • by AmiMoJo ( 196126 )

      Indeed, Google Assistant does local processing and remote processing at the same time. If the local processing is having trouble it can hand off to the cloud for more powerful voice recognition, and of course many questions require the cloud for an answer.

      By doing both it gives you the fastest possible response and is also highly reliable and works offline.

      Be interesting to see what the Apple patent contains considering other people are already doing it.

    • Well looks like Google is going to get sued for patent infringement. Why can't they come up with original ideas.

  • "Call Mom Mobile"... (Score:4, Interesting)

    by magzteel ( 5013587 ) on Saturday November 17, 2018 @05:14PM (#57661610)

    ... "I'm having trouble with the connection"

    That drives me insane. Siri should at least handle voice calls when not connected.

    • by pz ( 113803 )

      My feature phone could handle voice-directed dialing nearly 20 years ago, once you trained it.

      My current Android phone can handle simple tasks like setting alarms without any connectivity whatsoever, and with no training whatsoever. It amazes me each time.

      What is the problem with Apple's Siri?

    • by antdude ( 79039 )

      Hence why online requirement is stupid for many requests like this basic command.

    • by MobyDisk ( 75490 )

      ^^ THIS ^^
      The worst part is when it correctly transcribes it and shows the text to you on the screen THEN opens a Google search. Why would it send the string "Call Mom on mobile" to the search engine!? Sometimes it even spells the contact name the exact same funny way it is in my address book!

  • Because of course we all know that filing of a patent means the "invention" will hit the market real soon.

  • I discovered an open source project at https://snips.gitbook.io/docum... [gitbook.io] that already does this. This is not a turnkey device like Siri, but it seems to suggest the the cloud is not required to implement speech recognition.
    • Yep, no cloud required, no connection at all. First, you build an assistant using their web console, then, you download it, and finally, you install it on your target platform, and you're good to go offline. We are using it in some projects at work. If I may : fresh French tech ! Oh, wait, I read something about and older ...
  • half a year ago; reviewing how well ViaVoicehttps://www.youtube.com/watch?v=7CAkYs8PJT0 and Dragon Natural Speaking worked on vintage hardware back in the day: https://www.youtube.com/watch?... [youtube.com]
  • over half a year ago; reviewing how well ViaVoice https://www.youtube.com/watch?... [youtube.com] and Dragon Natural Speaking worked on vintage hardware back in the day: https://www.youtube.com/watch?... [youtube.com]
  • by fyngyrz ( 762201 ) on Saturday November 17, 2018 @07:50PM (#57661972) Homepage Journal

    Do any other phones/cars/speakers have this option right now?

    My Garmin nüvi 3597LMTHD GPS has done this since I bought it in 2013. It's not connected to anything, not wifi, not cellular, and not bluetooth. Where I live (the boonies) the traffic features and even the map updates are pretty pointless, so there's never been a need to connect it to anything. Yet it understands me just fine. And unlike Alexa and others, it allowed me to rename it — it only responds to "yo, bitch", which is just how I like it. :)

    Is the unit's understanding of language in general up to par with todays systems? No. But does it work for what it needs to understand? Yes. Very well.

    For the home, when and if MyCroft [mycroft.ai] gains a local speech understanding capability, that's the way I'm going. Everything I want to do is local, and the unit can be customized to run just about anything you put together (of course, commercial products aren't that easy to figure out, but that can be done in many cases as well.) Everything that depends on the "cloud" has failures, comm losses, and security concerns. Local is definitely the way to go.

    Otherwise, everything you say ends up sent to Google, Amazon, Apple or whoever. And whoever they partner with / roll over for / get hacked by.

    I trust Apple a little bit more as they've been pretty clear about being privacy focused, but that door is open for them to do "whatever" with your data, and it is best to keep that in mind. If they go local, that'd be nice. But inasmuch as it's a closed system, whereas MyCroft is an open system... yup, still going MyCroft if they can pull this off.

    • by Dantoo ( 176555 )

      Thanks for that. MyCroft looks good. Shipping is a disaster though so I'll have to wait until that gets sorted. It shouldn't cost more to post than to buy.

  • I've always assumed that the real reason to send the sound for external processing is so that it can be stored and analyzed.

    Smart phones have been powerful for a long time.

    Maybe now they can just process the voice locally and then send the data to the collection center.

    • I've always assumed that the real reason to send the sound for external processing is so that it can be stored and analyzed.

      Yup, as most people don't remember, Siri was created by an app developer and Apple bought it before the launch of the 4s... My friend had it, loved it, and it didn't need a data connection to do a lot of stuff. Once the 4s came out, it was deleted from his 4. I don't recall if he got a refund.

      Apple just wanted the voice data for pure analysis.

      You can still control your phone with voice options in accessibility settings to avoid sending your data to Apple via Siri.

      On an unrelated note, I think the developer

  • by Ronin441 ( 89631 ) on Saturday November 17, 2018 @10:27PM (#57662292) Homepage
    iOS already processes voice locally on the device. Cloud is only required for the Siri stuff. As proof, set an iOS device into flight mode, and open anything with an on-screen keyboard: edit a note, draft an email, etc. Tap the microphone icon, and talk. You'll see your speech transcribed with no resort to the cloud. (Misleading Headline is Misleading -- Film at 11.)
    • To your point, in notepad, the microphone works for text to speech, but voice commands won't play a local song on the phone or make a phone call.

      Try saying:
      Open iTunes
      Play Playlist Chillout

      After waiting 60 seconds:
      "I'm having some trouble with the connection. Please try again in a moment."

      So yes, it has speech to text, similar to the Commodore 64, but no commands work, even if the command doesn't need the Internet for anything such as playing a song loaded on the phone or opening the camera.

      • by Ronin441 ( 89631 )
        Sure -- cloud is required for the Siri stuff. And it makes sense that Apple would want to move Siri smarts for stuff that doesn't essentially require an internet connection (playing local music, etc) onto the device. My point is just that the Slashdot headline is misleading, conflating voice-to-text with Siri.

        (And the C64 had (as you say) text to speech, but most definitely did not have speech to text, which is of course orders of magnitude harder.)

One man's constant is another man's variable. -- A.J. Perlis

Working...