News - We need to talk about speech recognition

[HEXUS]

The natural way to communicate.

Read more.

[crossy]

Nearest (okay, there are others, but it's the most well known) alternative to Siri on Android is Vlingo. And Nuance bought Vlingo, (as it says in the article), so it kind of looks like they've cornered the market wrt speech recognition.

I've got Vlingo on my phone at the moment, don't use the speech recognition features, but the vocalisation of text messages etc is useful to me.

[krazy_olie]

2 reasons why it isn't popular:
1) it is actually very difficult, only scratched the surface of it when studying it but it's very complex.
2) (and this is the biggun really) you look and feel like an idiot!

[Roobubba]

I've toyed with voice recognition software on and off over the last 15 or so years, and it still doesn't feature as a useful thing, for me. I can type faster and with more accuracy on a keyboard. Furthermore, much of the time that I spend typing is done so in reasonably quiet environments, where it would not be appropriate to be speaking out loud. And then there are the noisy environments, where there are technical hurdles to overcome - like someone shouting over your shoulder, and suddenly your scientific paper has "Oi Roobubba, get me couple of jammy doughnuts too!" inserted randomly.

Don't get me wrong, I think it's a technology that would be great to have working properly, and it's getting quite close to being genuinely usable.

It's just not quite there, yet...

[bain]

The final test will be when it recognises Scottish accents.

[Hicks12]

I can never get on with the voice recognition software, I want to like it and I can sometimes get it to work almost flawlessly with my voice BUT and this is a big but, I cant be productive with it...Me personally i have to just think to myself and type it down, it is a seperate process for me but as soon as I try and change the typing to just listening/voice recog then my way of thinking has gone, i start thinking in my head more and more and it puts me off talking to myself (yes i talk LOADS when discussing a problem with myself :L) as the system will take what i say.

I even have an issue with if i do manage to concentrate enough to realise what i need to input, the issue is i lose track of progress, my mind just cant comprehend talking to the system WHILE thinking what i was meant to speak. As above typing just works for me, i tell myself what i need to type and boom it transfers and my hands have already dealt with that, occasionally something gets missed but its relatively low.

If i could get passed that barrier i wouldnt mind at all, only for my home pc mind as you look like a total tool using voice recognition in public! And for Siri, it really isnt there at all... my friend was trying to show off with it and it didnt work 90% of the time... its really pointless for phones and i cant see myself being the only person who thinks the whole point of voice recognition is for handsfree, yet with Siri you have to press the start button... if you are only touching your phone im sure its easier to just TYPE the line you want to search in google or hit music than way for Siri to make the noise and you talk and then wait for it to load.

[Andeh13]

I gave up replying to this because my phone keyboard is.lagging(galaxy nexus s, customROM) and I am at work so can't talk to my phone! Dammit

[Saracen]

I've toyed with voice recognition software on and off over the last 15 or so years, and it still doesn't feature as a useful thing, for me. I can type faster and with more accuracy on a keyboard. Furthermore, much of the time that I spend typing is done so in reasonably quiet environments, where it would not be appropriate to be speaking out loud. And then there are the noisy environments, where there are technical hurdles to overcome - like someone shouting over your shoulder, and suddenly your scientific paper has "Oi Roobubba, get me couple of jammy doughnuts too!" inserted randomly.

Don't get me wrong, I think it's a technology that would be great to have working properly, and it's getting quite close to being genuinely usable.

It's just not quite there, yet...

I hear all you say, and agree with the points you make, but for me, it is here now, does work, and is eminently usable.

I too having been dabbling for about 15 years, but go back anything like that far and, IMHO, their software wasn't polished enough but more importantly, the computer power to do a creditable job just wasn't there. It is now.

That's not to say it's perfect, and it certainly isn't of StarTrekian smoothness. But usable? Hell, yes.

My experience with Dragon is that it's usable, to a very high level of accuracy, right out of the box, given only a 5 minute "sample" of your speech. And the more you use, and correct, the better it gets. But, you need adequate power (which almost everyone now has), you need a good and suitable mic/headset, and you need to train yourself a little. Speaking with clear and distinct enunciation, rather than the lazy and sloppy way many/most of us now converse, helps. The closer you can to the sort of clear and distinct speech we used to get from BBC news people would help, though I stress I'm talking about style, not the clipped Oxbridge accent.

All it really needs, given the power and mic, is a speech style where words are pronounced distinctly, and not runintoeachotherlikethis. I have to concentrate a little to do that, from my more normal conversational style, but if I do, then I get about 99% accuracy, and I don't know about you but my typing can't match that when I'm at my best, let alone when I type quickly. Maybe your keyboard skills are better than mine, but for me, Dragon 10, and certainly Dragon 11, are easier and faster to use for a block of type than typing. I don't bother for brief passages, but for longer pieces of work, Dragon has paid for itself in time saved over and over and over again.

On a phone, though? Not so convinced. Partly, that's because I don't do the type of work on a phone that would really benefit, and partly because given the power of the phone, and the "server" nature of the apps, I doubt the process would be smooth enough to appeal to me. Having said that, I haven't tried it.

[MaddAussie]

Its the one thing I miss from my blackberry was the ability to pus a button (either on the phone and on more importantly on the head unit in my car) and just say 'call xyz mobile' and it would call whoever (struggles when the roofs down a bit ) if anyone knows of an app that does this on android please let me know!

[TaintedShirt]

@MaddAussie If you have android just long press the search button and it brings up the voice search options, usually Google Voice.

I have Vlingo, Dragon Go and Google Voice installed. I have just tried calling someone with my phone using each of these. Google Voice was the only one to get even close and eventually actually did give me the option to call the person. I had to modify the way I speak. It also gave me several choices so I would have had to press the correct option so not really hands free.

On my very old Windows ME phone I use Microsoft Voice Command. This worked easily, I could ask it to call someone, it would repeat the command to me giving me time to stop it (by saying "No") if it was the wrong command. If I said nothing it would then actually dial for me. I could ask it the time, when my next appt was, to look up people (contact details). All this worked really well and it was all on the phone. Years later I have a phone that is way more powerful but less capable. Go figure.

[crossy]

Its the one thing I miss from my blackberry was the ability to pus a button (either on the phone and on more importantly on the head unit in my car) and just say 'call xyz mobile' and it would call whoever (struggles when the roofs down a bit ) if anyone knows of an app that does this on android please let me know!

I'd go raid Market Place - sorry "Google Play" - and download a selection (most of them are either free or have "trial" versions.

Latest Vlingo has a "car" mode that purports to be able to operate fully "hands free" (presumably via some keyword that it's listening for). However, I'm not convinced that it's flexible enough to be able to allow you to select a particular contact's mobile, rather than just chosing the primary number in your contacts book.