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

Using Voice to Code Faster than Keyboard

ergoemacs.org

Post reply on HN
Print view View original

131–137 of 137 posts

Re: Using Voice to Code Faster than Keyboard

#131

Post by tavisrudd »

Hi, I'm the guy in the video. You might also be interested in a presentation I gave last Sept at Strangeloop with a much longer demo of coding in Clojure and Elisp: http://www.infoq.com/presentations/Programming-Voice

There's also this lightning talk http://www.youtube.com/watch?v=qXvbQQV1ydo from PolyglotConf (warning: crappy audio from a shaky cell phone cam).

I promised to release my duct tape code later this year. I'm a bit behind schedule with that but it should be out in a month or two.

Re: Using Voice to Code Faster than Keyboard

#132

Post by tavisrudd »

fsck--off wrote: post #25

"Emacs pinkie" is a non-issue if you use a keyboard with thumb clusters, e.g a Maltron or a Kinesis model. Investing in a good keyboard is just as crucial as investing in a good chair, especially if you make a living by coding. The time that you spend compensating for a bad input device by hacking your own workarounds can be more costly then spending money on a proper solution. Once you are an adequate touch typist t…

I used a Kinesis for many years and had a great chair and ergonomic setup before developing the RSI that I describe in the video.

Re: Using Voice to Code Faster than Keyboard

#133

Post by tavisrudd »

WalterSear wrote: post #53
mhd wrote: post #36

Earlier quoted context omitted.

A high-quality headset, maybe even with some noise-canceling features should work okay, too. It wouldn't be that much different from a call center, and those don't usually get their own offices, either. Sure, not the ideal, distraction-free environment, but neither is a cubicle farm.

Voice recognition isn't good enough for that yet: hyper-cardioid mics can only do so much.

The mic I used in the video can actually cope with very noisy environments. With lesser mics, speech recognition is useless with even mild background noise.

Re: Using Voice to Code Faster than Keyboard

#134

Post by tavisrudd »

unclesaamm wrote: post #22

Okay, here's the million dollar question that isn't on the FAQ and no one in the audience asked. How the hell did he code it without using his hands? With help? To his amanuensis: Slap. York. Tork. Jorb. Chomp. Or maybe he felt his hands going, and he spent the last few months of his pre-RSI existence coding this up.

Once I got the basics working with the DragonFly and Natlink libraries I mentioned, I bootstrapped the rest mostly by voice.

Re: Using Voice to Code Faster than Keyboard

#135

Post by tavisrudd »

thenomad wrote: post #73
mechanical_fish wrote: post #57

A few months ago I had an RSI problem so bad - able to type only a minute at a time, even sitting with hands on keyboard hurt - that I started down this route. This video was, literally, a life-altering motivator for me, and I was quite obsessed with it. Ironically, after seeing a physical therapist - which, let me tell you , you should do at the first sign of pain, because while they can't help some people I persona…

Having suffered with RSI for years (before the advent of current-gen speech recognition, so it really sucked), I heartily echo this advice: which, let me tell you, you should do at the first sign of pain Do that. REALLY REALLY do that. Also, this book is superb: http://www.amazon.co.uk/Its-Carpal-Tunnel-Syndrome-Professio...

Great book!

Re: Using Voice to Code Faster than Keyboard

#136

Post by charlieflowers »

DigitalJack wrote: post #114
charlieflowers wrote: post #94

Question (halfway on topic) -- Who makes the best speech recognition software in the world? Regardless of whether it is available to consumers ... who is the best at it? In particular, how do Apple (Siri) and Google (Google Now) compare to Nuance's stuff? Is Nuance so far ahead of everyone else that they're the clear leader? Or is their codebase "legacy" and vulnerable to better, more accurate software which can be b…

I don't know who makes the best. But I know the history behind dragon is very sad. http://en.wikipedia.org/wiki/Dragon_NaturallySpeaking#Histor...

Wow! That would lead one to speculate that perhaps they haven't had the best of engineering teams focused on improving the product over the years! Which means there might be a huge opportunity here.

Re: Using Voice to Code Faster than Keyboard

#137

Post by brownbat »

tavisrudd wrote: post #131

Hi, I'm the guy in the video. You might also be interested in a presentation I gave last Sept at Strangeloop with a much longer demo of coding in Clojure and Elisp: http://www.infoq.com/presentations/Programming-Voice There's also this lightning talk http://www.youtube.com/watch?v=qXvbQQV1ydo from PolyglotConf (warning: crappy audio from a shaky cell phone cam). I promised to release my duct tape code later this year…

Strangeloop was a great demo.

What's the next big leap for speech to text programming? A language designed specifically to be speakable, ie, all keywords and no symbols?

I mean, I'd like speech recognition to get more natural error correction, drawing more from the way we use inflection to give feedback about which syllables to correct. (I love how Google on mobile now gives visual indication of which syllables it heard clearly, and which it didn't. I just wish it would understand when I shout "No, X not Y" to replace just that one misheard word.)

It'd be interesting to hear about where voice is heading from someone who uses the technology far more.

Post reply on HN