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

51–60 of 124 posts

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

#51

Post by willcipriano »

fouc wrote: post #31
PaulHoule wrote: post #5

Google and Siri are good at what they do. They aren't good at other things, such as dictation. I see the big problem in voice interaction is that a human being will ask you questions to clarify what you said if they don't understand and current systems don't even try. (Actually the search paradigm lets you do some refinement, "Ok Google" works amazingly well on Android TV.) Superhuman accuracy at dictation doesn't tr…

I would imagine GPT-3 or similar would be able to fix replace the garbled 1 out of 20 words with something that actually make sense in context.

How do you know what word is garbled?

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

#53

Post by calchris42 »

Wow, so many replies that boil down to “because typing is better, you should just type”.

This is fairly insulting as RSI’s are very much a real thing.

Does this community also think that wheelchair ramps should never be invested in because stairs are clearly superior?

I’d rather see the brain power in this community focused on solutions. Keyboard + mouse have lasted so long because they work surprisingly well, but I hope there is a day that we dream up something better that does not require slowly giving ourselves carpel tunnel.

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

#54

Post by imglorp »

Klaster_1 wrote: post #8

Is there a high quality voice control for anything? I only ever tried Google Assistant and it mostly always can't comprehend queries beyond "timer 10 minutes", like putting a water boiler on schedule.

GA is also tightly limited by business constraints.

  "Send a slack to my wife" -> "Sorry, who do you want to text?"
Multi-fail.

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

#56

Post by robbedpeter »

willcipriano wrote: post #51
fouc wrote: post #31

Earlier quoted context omitted.

I would imagine GPT-3 or similar would be able to fix replace the garbled 1 out of 20 words with something that actually make sense in context.

How do you know what word is garbled?

Grammar and context. It'd be closer to dictation than current speech to text, with gpt serving as a "brain" interpreting what you mean in the current context instead of raw input. You could tie in the "natural language to [sql,bash,log parse, regex]" capabilities of gpt-3 and so on.

Obviously it wouldn't be as good as a real person, but it'd be a nice leap to the 95%+ level of accuracy over the 80%ish on high performing commercial STT systems.

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

#57

Post by mertd »

falcolas wrote: post #35
6gvONxR4sf7o wrote: post #18

Earlier quoted context omitted.

Keyboard and mouse certainly don't beat voice for bandwidth (assuming error-free ASR, which doesn't exist today).

This guy's not wrong. You can speak clearly and comfortably at 250 words per minute. Most folks will type at less than half that. Even shortcuts (which peer comments are relying upon) aren't all that fast - they require additional selection movement with the keyboard or mouse before they can be used.

People do much more than narrating natural language. They navigate menus, highlight text, launch apps, type commands on the terminal etc... I don't see how voice can best keyboard and mouse when considering all interactions.

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

#58

Post by adolph »

viro wrote: post #21

... because it's not a good way to control a computer?

> ... because it's not a good way to control a computer?

This comment speaks to a perception problem for aural methods. The state of the mainstream art doesn't seem much past Forstall's demo of 10 years ago. [0] Are generations of people accustomed to WIMP UI able to wrap their heads around a much smaller interaction set? [1]

Gentner and Nielsen's work described in "The Anti-Mac Interface" [2] speaks to some of the differences people will have to mentally bridge such as:

  Mac | Anti-Mac
  Direct Manipulation | Delegation
  See and Point | Describe and Command
  WYSIWYG | Represent Meaning
  User Control | Shared Control
  Feedback and Dialog | System Handles Details
  Forgiveness | Model User Actions
0. https://www.youtube.com/watch?v=SpGJNPShzRc

1. https://en.wikipedia.org/wiki/Post-WIMP

2. https://web.archive.org/web/20120904231532/http://www.useit....

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

#59

Post by phkahler »

I would like to see Linux lead here. Have a standard voice interface where a voice-to-text process feeds a stream of text to the DE, which can then forward it to the active application (as text). I want this to be a separate "voice" stream so it is not confused with the keyboard. This would allow the eventual creation of a voice assistant at the system level, but also allow individual applications to adopt voice commands starting now. IMHO this should be like version 1 of the concept and it should last a while until we figure out what all is possible and which use-cases need a design change.

Simple dictation could be done at the DE level, where the VtoT stream would be diverted to the keyboard input of the active app. It could also be done at the app level, but this is one feature I think belongs a level up so it can be used by non-voice enabled apps.

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

#60

Post by jbellis »

maxore44 wrote: post #42
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…

I am a cursorless user myself. Using dictation software for programming is actually relatively fast when you get used to it, but editing code (which is how most of us spend the majority of our time) can be pretty slow. Cursorless was a huge productivity booster for me. It got me to switch from Emacs to VS Code which is saying something.

What distinction are you trying to make between "programming" (fast) and "editing code" (slow) ?
Post reply on HN