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

Ask HN: Why is there no high quality method for voice control of a PC?

news.ycombinator.com

Post reply on HN
Print view View original

101–110 of 124 posts

Re: Ask HN: Why is there no high quality method for voice control of a PC?

#101

Post by Stevvo »

WorldMaker wrote: post #83

The last time I tried Dragon it was just a fancier (bloatware) UI built directly on top of Windows Voice Recognition (and IMO not adding much value on top of it): https://support.microsoft.com/en-us/windows/use-voice-recogn... Windows Voice Recognition has been around forever (out of the box since XP), it's UI is "serviceable" but not great. (It was slightly better when Cortana was briefly "out of the box" in Windows…

Not sure where you got that idea. Dragon predates Windows and has always used its own models.

It works very well for some people; many have written books with it.

Re: Ask HN: Why is there no high quality method for voice control of a PC?

#102

Post by daanzu »

dataangel wrote: post #99

I have an RSI and I've been coding by voice exclusively for about 7 years. I used a system built on top of Dragon for most of that and in the last year switched to Talon. I think there are multiple reasons: * The obvious market is dictation of natural language, but this isn't what you want for voice control. If you try to use long descriptive phrases as your command language everything takes forever. So instead you e…

"Everything other than talon has terrible latency": False! I develop kaldi-active-grammar (https://github.com/daanzu/kaldi-active-grammar), a free and open source speech recognition backend, which has extremely low latency. You can adjust how aggressive the VAD (voice activity detection) is to suit your preference, but the speech engine latency can be almost negligible, especially for voice commands (vs prose dictation). However, I agree that "most existing speech recognition engines were not designed with the kind of latency you want for quick one syllable commands", and that low latency is pivotal to being productive with voice commands. I also agree with your other points.

Re: Ask HN: Why is there no high quality method for voice control of a PC?

#104

Post by wnolens »

falcolas wrote: post #29
wnolens wrote: post #14

That sounds exhausting. "Open this program" "Minimize" "Focus on this text input" ..dictate.. "switch to command mode" "save and close" i'd rather just: "click click tab type ctrl-S"

The actions are a bit more like "move mouse to this 100x100 pixel square, click twice within 100ms" "move mouse to this 20x20 pixel square, click once" "Move mouse to this 100x1000 pixel rectangle, click once" "Type text at a rate 1/5 (1/2 if you're particularly fast) speaking rate" "Move your pinkie (your weakest finger) to 'ctrl' and click, move your index to 's' and click, release both, verify it worked with a vis…

You're right. But OP didn't understand why it doesn't exist because "market is so big."

I presumed they meant more than the extreme edge of RSI sufferers. So I ran the thought experiment.

I've had a mild RSI. The solution was get fancy ergo mouse/keyboard/desk/chair, and retrain myself. I've even seen a guy use a joystick instead of a mouse.

Re: Ask HN: Why is there no high quality method for voice control of a PC?

#105

Post by newusertoday »

daanzu wrote: post #100

I have been coding entirely by voice for approximately 10 years now (by hand long before that). Most of that time I have been using the Dragonfly ( https://github.com/dictation-toolbox/dragonfly ) library to construct my own customized voice coding system. The library is highly flexible and open source, allowing you to easily customize everything to suit what you need to be productive. It is perhaps the power user an…

what sr engine do you use for your personal setup? is it kaldi?(assuming you helped developed it :-) ) .

Re: Ask HN: Why is there no high quality method for voice control of a PC?

#106

Post by Avatars »

"Why is there no high quality method for voice control of a PC?" For the same reason there's no standardized encryption for everyone's comms. Or, 'Why is there no software for gps that works on pc's that is easy and readily available?'. Same reason.

There is a voice assistant ap for Android that uses vosk called Dicio (f-droid). Storage is cheap and easy. Processing power is there even in cheap 3rd world phones. I personally detest typing and would love to talk to my devices without any 3rd party nonsense requirements. Truly there is none because the powers that be do not want everyone thinking they are in control, essentially of anything.

Re: Ask HN: Why is there no high quality method for voice control of a PC?

#109

Post by newusertoday »

I tried using talonvoice but the recognition engine failed to understad lot of words. I then searched for pronunciation of those words on google and tolonvoice detected them correctly. In the end i learned to pronounce the words in american english so that talonvoice can understand them ;-) .Not what i was hoping for, i wanted to teach computer to recognize my voice not the other way around.

Re: Ask HN: Why is there no high quality method for voice control of a PC?

#110

Post by jiehong »

pokeyrule wrote: post #47
ahelwer wrote: post #13

I've heard cursorless ( https://github.com/cursorless-dev/cursorless-talon ) is good but have never tried it. Syntax-aware voice navigation of code, powered by tree-sitter queries! I also have a friend who is a gifted programmer who lost his ability to type about a decade ago; he has put together an open-source software stack to help: http://www.cs.columbia.edu/~dwk/ Of course this doesn't really answer your question…

creator of Cursorless here. Happy to answer any questions

Seriously cool project!

This reminds me of easy motion for vim or ace-jump for emacs.

Do you think it would be possible to have an on-demand contextual hat decoration?

Like you say “show hats words” and only words get decorated with hats and you pick one. It would allow you to maybe show hats only on square brackets or only on function arguments, etc. I find the number of hats with colors a little bit hard to distinguish; should they were contextual, they would require fewer or no color.

Do you map voice commands to keyboard shortcuts available in vs code, or directly via the apis? (Not sure if there is a difference in the end).

Now I wish for a cursor less plugin on the IntelliJ platform.

Post reply on HN