The Coming Wave of Gadgets That Listen and Obey

dgan brings us a NYTimes piece about the development of speech recognition for common gadgets. Companies such as Vlingo and Yap are marketing their software to cellular carriers to give consumers a hands-free option for tasks like finding directions and text messaging. Quoting: "Vlingo's service lets people talk naturally, rather than making them use a limited number of set phrases. Dave Grannan, the company's chief executive, demonstrated the Vlingo Find application by asking his phone for a song by Mississippi John Hurt (try typing that with your thumbs), for the location of a local bakery and for a Web search for a consumer product. It was all fast and efficient. Vlingo is designed to adapt to the voice of its primary user, but I was also able to use Mr. Grannan's phone to find an address. The Find application is in the beta test phase at AT&T and Sprint. Consumers who use certain cellphones from those companies can download the application from vlingo.com."

The increasing rate of change Collective Power

[FromTheAir]

I can imagine the day we speak the name of some legislation in the phone and say "vote yes" or "vote no". The results show up on our congressman's web site and some other third party sites that archive. This way we take control of a few and transfer it to the less corruptible and wiser "many".

Re:It may finally happen.

[peragrin]

nope. because we must select double delete them all.

voice recognition is no where near reliable. I laugh at my brother as he tries to use voice dial on his cell phone, it takes two or three times to get it to work. I once sneezed and it dialed my father. a good throat clearing sounds like mother. I should try farting at it some time to see who that would Dial.

Seriously try it sometime. delicately train the system for your voice, use it for a while, and then start throwing random noise at it. Or take a song which the music track is quiet enough to hear each word clearly and play that at the microphone. It should give you all the lyrics, yet they can't sort that out. The human ear can, but a computer can't yet. voice recognition is nearly useless until it can.

Limited phrasebook

[name*censored*]

Limited phrasebook technology is a lot better than voice recognition technology in a lot of devices. Given that most (well, all) devices have limited functionality (not even Steve Jobs' iPod can do his taxes for him), there's very little point in giving the device the ability to understand possibly-misdirected phrases such as "Honey, have you seen the remote?". A good approach for this technology would be to limit it to understanding alternate ways of phrasing a particular command; "Device, Get Me A Beer"/"Device, Can I Have A Beer"/"I'm Really Thirsty". This way, we'd avoid misdirected speaking (the device thinking you're speaking to it instead of to another), and could also exploit the reduced set of understandable phrases to correct for people with colds/accents/quiet voices/etc, in much the same way as limited-phrasebook devices work (only with more flexibility).

Re:I wonder...

[Amorymeltzer]

Everything. I personally don't give a rat's ass about cell phones - it's not really a big deal or very innovative until you just have a communicator built in. Everything else though, from doors, lights, running tasks on a computer, etc. is what's really cool. Little inane things that just piss you off in life - like having to get up from the bed with the girl/boy on it to turn the light off, or setting a TV up for a movie, or having the computer do everything you want. I'd much rather say "wait until this song ends, then play "Helter Skelter," and then put up an away message and turn the display off." (Not that I can't really do that already, it's just more aggravating)

Re:It may finally happen.

[ScrewMaster]

The human ear can, but a computer can't yet. voice recognition is nearly useless until it can.

Voice recognition is incredibly useful in the right context. A friend of mine is an attorney who happens to be disabled. He makes great use of voice recognition on his computer, does most of his legal work with it. Is it "conversational"? No, but it serves his purposes perfectly.

So you're right, speech recognition systems aren't as generally versatile or accurate as the human brain, but they're getting better all the time. Give it ten years or so, with improved algorithms and a sixteen core processor to handle them I think we'll be interacting with computers on a much different level. Of course, by then you'll have to know Spanish or Mandarin to use one of them.

Re:I wonder...

[FromTheAir]

There is no reason you couldn't set your car's speed with your cell phone using Blue Tooth. Just say 80 MPH please. Or reduce rapid, no break lights, 60. Or speak "reduce 3 spot 60 BL not." That means reduce speed to 60 in 3 seconds no break lights. Over the course of 3 microseconds the car determines based on recent stored values if there is another vehicle approaching from behind and how close speed and if a collision would result from your command. If not it executes the command. Everyone could be tweaking the safety parameters to have the fastest vehicle. With enough sensors and computerized control we could travel much faster safely. Of course there is an issue with voice command in an environment with lots of noise pollution. Of course why not just tell it your destination and have it automatically race like a bat out of hell, coordinating with all the other cars on the road, to get you there while change stations on the stereo and recline the seat. Obviously we would engineer any big brother features out of the traffic intelligence system creating autonomous anonymous intelligent navigation.

Re:heard it all before

[mdfst13]

It just isn't much faster than typing

Sure, but it's a lot safer to do while, say, driving down the road. The problem with screen output and typed input is that you have to use both eyes and hands to operate the device. By contrast, using speech input and output only requires voice and ears. Of course, there are some circumstances where the screen/type method is superior, e.g. sending emails from your blackberry during meetings. However, there are many cases where speech is superior, e.g. driving down the road (or even just walking). Viewing speech as a replacement for screen/type is over zealous. It's really more of an alternative.

It would probably help if advocates of the technology understood this. It doesn't have to be all or nothing. Two alternative solutions can add up to a more powerful solution than either would be alone.

Re:All I can think of is...

[value_added]

"Open the pod bay doors, HAL."
"I'm afraid I can't do that, Dave."

My take on the matter is that the reason that's all you can think of is that everything else is inappropriate, inefficient or simply too goofy for consideration.

Not to anthropomorphise electronic devices (I know, they don't like it when you do that), but I think they'd prefer to be treated anonymously and respond the most basic of instructions only. And we'd prefer they remain that way, except in very limited circumstances where the device is named Lenore.

In the Star Trek movies you'll find something similar to the above, with an occasional "Tea, Early Gray, Hot" for good measure, but the rest of the time everyone is interacting with devices using ... wait for it ... keys and buttons. And this is into the technologically advanced future where most everything is a device, including crew members. Seeing Picard, for example, say "Computer, send a message to Data telling him to work on his joke-telling skills", or to use the article's example, [asking] his phone for a song by Mississippi John Hurt, would be seen by everyone as a ridiculous use of technology and dismissed as absurd.

Voice recognition, in the abstract, is fascinating and no doubt fun, but I wouldn't want to live in a Tourettes-like world where everyone is shouting out instructions to unthinking devices, let alone work in a cubicle where the next guy's phone conversation are competing with the noise of his regular work.

So past opening and closing doors, keyboards it is. Or for those unskilled in the expressive art of the command-line, a mouse or function buttons.

Re:Cell phone vs. server farm

[Simon Brooke]

...what?
Please mr. guru, tell me how this happens exactly.

I not saying it is done that way, but it would be very easy to do it that way. Mobile phones have all the kit which is needed to digitise speech, and to send that digitised speech over a GPRS connection to a web service that does speech-to-text and returns the text would be trivial. Doesn't need a guru.