Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

25 Years In Speech Technology and I still don’t talk to my computer

matthewkaras.medium.com

Post reply on HN
Print view View original

261–270 of 296 posts

Re: 25 Years In Speech Technology and I still don’t talk to my computer

#261

Post by swiley »

Because none of them are an improvement over a shell.

Maybe if there were a better way to pronounce "open paren" and "make-vector" we could just yell scheme at the nearest computer.

IMO you're never going to get anywhere trying to make shells speak natural language. Even if you crammed a person into the box there's just way too much you could ask to narrow it down without something formal. At the end of the day you'll have to have something that looks like sh or any other formal language.

Re: 25 Years In Speech Technology and I still don’t talk to my computer

#262

Post by 6gvONxR4sf7o »

I'm dictating this. Not going to make any corrections, so that you caan see what the state-of-the-art is right now, including bugging us (that supposed to be bugging this. Apparently it doesn't recognize that word it's the quality of being buggy).speech is my primary interface my computer due to health issues, and my God is it infuriating.it's never going to really take off until it just works.

imagine if your keyboard had about a 2nd latency and every couple words got messed up in some way. Not only that, but those same words that got messed up are probably getting be messed up again when you try to go back and fix it with the same broken keyboard. you wouldn't say that typing is nearly solved, you'd say that typing absolutely sucks and keyboards just don't work.

I firmly believe that speech is going to be the main interface-actually want to scratch that last sentence, but correcting it is can the pain with voice. I firmly believe that speech is going to be a game changer of an interface, especially for coding, eventually. But until it stops sucking, it's only can be used where where there is no other choice.

(By the way, this is me, a native English speaker with a standard salmon Cisco accent-that's a standard San Francisco accent- dictating it on a many hundred dollar microphone into a many hundred dollar speech engine, speaking relatively slowly and enunciating the hell out of out of things.when I first started with that, it was even worse. and yet somehow a lot of people treat speech recognition as if it is in some way solved, or the error rate is better than human.or loader ship-that's supposedd to be what a load of ship-whatever you see what I mean)

-----

(edit: After the fact, I decided to calculate the word error rate dictating thhis. About 7%. If you ignore the non-speech-related bugs, it's about 4%, which is supposedly "superhuman." take that as you will. my take is that "human level" is not the same as a human trying to work as fast as they can, and maybe not paying particularly close attention. And that 4% is ridiculously far from 0% in terms of usability)

Re: 25 Years In Speech Technology and I still don’t talk to my computer

#263

Post by mikestew »

justinlloyd wrote: post #248
mikestew wrote: post #185

Earlier quoted context omitted.

I live in Redmond, WA. Frankly, if someone asked to meet for a meal at eighteen, I would assume they would like to get together in a Microsoft cafeteria closest to the (what I believe to be non-existent) Building 18. My backup option would be to assume that they have received a hard blow to the head at some point in their life. Again, whether I would understand them or not, no one to my knowledge speaks like that in…

Officially building 18 does not exist. Anything you may have heard about building 18 is just rumour. If you have any questions regarding the purpose of building 18, you should direct them to Shelley in HR.

Hey, it's been well over a decade since I worked there. :-)

https://campusbuilding.com/b/microsoft-building-18/

Re: 25 Years In Speech Technology and I still don’t talk to my computer

#264

Post by 0xffff2 »

ryandrake wrote: post #150
PeterisP wrote: post #137

Earlier quoted context omitted.

GUIs won over console workflows because GUIs have better discoverability and the "recall vs recognize" difference; it's mentally much easier to recognize the option you want when presented it than to recall the existence or the naming of that option. In those aspects of UX, voice interfaces have the same drawbacks as console apps when compared to a good GUI. Also, they have to work within the "bandwidth bottleneck" o…

> Also, they have to work within the "bandwidth bottleneck" of audio - just imagine a phone system that tells you all the options you have, "Press 1 for something, Press 2 for another thing..." - they are so annoying because they are slow and inherently linear They're even slower now because the brain trust decided adding voice control to the phone menu system was a great idea. So before, it said "For prescription re…

Honestly, "Tell me what you want!" is better than a system that forces you to listen to all of the options since "representative" is what I want 99% of the time when I have exhausted all other options and decided to do battle with an automated phone system.

Re: 25 Years In Speech Technology and I still don’t talk to my computer

#265

Post by aYsY4dDQ2NrcNzA »

XCSme wrote: post #148
toolslive wrote: post #79

Back in the days (80s) they were joking about the programming languages used in early (star trek) holodecks. > (1st attempt) "Computer! coffee please" > (computer dumps coffee on Kirk) "argh!" > (2nd attempt) "Computer! coffee in a mug please" > (3rd attempt) "Computer! hot coffee in a mug please" .... > (25th attempt) "Computer! 10cl of coffee at 50C with 3cl of fresh milk at 6C in a bottoms down ceramic mug of 15cl…

This means that you whould only be able to choose between several (discrete) choices instead of assigning the computer random tasks. But when the number of such choices is really small (eg. make coffee), then a simple physical button to initiate the task is better in almost every way.

“Computer. Press the coffee button.”

Re: 25 Years In Speech Technology and I still don’t talk to my computer

#266

Post by asdff »

dheera wrote: post #5

A big problem with the assistants is that as soon as they fail at a query they seem stupid, I feel stupid, and I stop using them for a long time. Last weekend I had the following failed queries: "OK Google, what is the air quality like at Mt. Shasta today?" "OK Google, add a waypoint for the last gas station before the mountain pass" "OK Google, what percentage of people can you detect to be wearing masks on recent I…

The big power of GUI is that it was an alternate control scheme to do anything you can do on the CLI. Voice control is not a UI. It's a limited set of functions not meant to offer analogous control over any aspect of your device really; if it does it's happenstance. That's why Siri is for setting alarms and not doing complicated workflows that would require your thumb. I wish it was a voice ui, though. I wish I could stick my phone on a shelf and step back and tell Siri to take a picture, to do that function on the phone my thumb can do, but the best Siri does is open the camera app because the voice controls are just that, a limited set of control levers to pull and not a complete user interface.

Re: 25 Years In Speech Technology and I still don’t talk to my computer

#267

Post by jrlnm »

6gvONxR4sf7o wrote: post #262

I'm dictating this. Not going to make any corrections, so that you caan see what the state-of-the-art is right now, including bugging us (that supposed to be bugging this. Apparently it doesn't recognize that word it's the quality of being buggy).speech is my primary interface my computer due to health issues, and my God is it infuriating.it's never going to really take off until it just works. imagine if your keyboa…

I think the issue with typing via voice are: 1) Speech accuracy 2) Correcting things by voice

It's super unnatural to correct things by voice and until we re-imagine what it looks like if we HAD to type via voice, it's gonna be painful.

(Speaking as someone who types via voice as well). Have used Dragon and now currently Talon

Re: 25 Years In Speech Technology and I still don’t talk to my computer

#268

Post by stiray »

Imho, the issue with speech technology is that it is beeing developed by companies that wants to abuse your home (device,...).

There is just no way I will let google device that listens my conversations let at my home (let me be faster - no, my phone doesnt listen, and yes I am sure, its maker wouldnt recognize it any more).

Or amazon. Or facebook. Sure speech technology could be usefull but not from those companies.

On the other side, there is just no usable way found by anyone else, how to monetize the technology (i.e. except for spying on people).

I think that this is THE problem of speech recognition.

Re: 25 Years In Speech Technology and I still don’t talk to my computer

#269

Post by Barrin92 »

matthewdgreen wrote: post #180
ineedasername wrote: post #162

Earlier quoted context omitted.

On your searches: 1) I get the correct response; Assistant first asks me if I want to use "air check", I say yes, and get the correct response. 2) I get appropriate responses when I ask "What is the closest gas station to Mt. Shasta." Because the approaches are mostly from Rt. 5, you'll have no problem getting a usable response. Another approach from Rt 89 exists, so I don't know how you expect Google to know which "…

I don’t believe he’s looking for a voice assistant. He’s in the market for Lieutenant Data.

the entire value of a (voice) assistant is that it can quickly and reliably deliver results. You don't need Data, but the system needs to be robust enough to work quickly. If you have to ask five times or spend minutes thinking about how to phrase the question, it's not assisting you in anything but wasting your time.

Re: 25 Years In Speech Technology and I still don’t talk to my computer

#270

Post by maneesh »

GloriousKoji wrote: post #132
maneesh wrote: post #33

Earlier quoted context omitted.

Weather is also useful! Sometimes reminders, which are basically timers. But yea that's it.

Siri doesn't get the weather right. "What's the weather in Yosemite" and "Yosemite weather" can get you two drastically different results. As of right now (10/26/2020 10:35 AM) the two results I get are 43F and 32F.

Siri is always mistaken. Alexa is pretty good.
Post reply on HN