Vista voice recognition instructional video |
Earlier today I was talking to a friend of mine who is disabled about voice recognition. We discussed how a good voice recognition system might help him accomplish more on the computer faster. He mentioned one of his frustrations was that the voice recognition systems he tried couldn’t get a good, workable sample of his voice which is low, raspy and without a lot of inflection.
Tonight, coincidentally, through my normal reading I came across a Vista Voice Recognition Podcast by Chris Henley. This video shot with Camtasia was really well done, but I noticed that even with Mr. Henley’s very clear voice there were a couple hiccups like where he said “bill gates” and the program recognized it as “build.” Overall though it seemed like it was handling his speech very well. It showed off the built-in (no extra software, cool!) speech recognition features in Windows Vista which “… should be out by Thanksgiving.”
I’ve spent very little time with speech recognition functions on the Tablet PC, but I’ve been impressed with the quality of that engine. It’s my understanding that the Vista speech recognition is even better. I’d definitely be willing to use speech recognition if it could save me time. Blogging by voice seems particularly appealing to me because I speak much faster than I type, but to date with all the editing and insertion of HTML I’m not sure how this would work in reality. Theory it sounds good.
The real test is when somebody like my friend tries this out. How does the speech recognition perform under those conditions? What I saw on the video was promising and certainly makes me a little more excited about Vista. Hopefully it performs that well for somebody who really, truly could use this to make their computing life better.
Related Posts- How to use speech to text dictation mode with the Tablet PC
- Why Linux on Tablet PC?
- When will Vista really come out?
- Gates dreams of $500 student tablet
- Improve Tablet PC Handwriting Recognition
- How long does it take to boot Windows Vista?




Yeah, SR could be good for blogging the first rough cut — spewing out the naked text, then use the mouse and keyboard to give it a bath and some new clothes. I’d give it a try.
Comment by Sterling Camden — March 1, 2006 @ 3:08 pm PST
From what I’ve read, if you’ve got an app running on Vista that’s specifically speech-enabled, you can easily create an XML dictionary of likely words or phrases that the app will read first before it hits the speech engine’s default dictionary. Just like ink-enabled TabletPC apps, this should provide a substantial boost to the recognition rate.
I’m really looking forward to it - I’m working on a project that’d be quite cool if I could easily generate phoneme & viseme data on the fly… And through a native API, no less.
Comment by protected static — March 2, 2006 @ 9:53 am PST
Speaking of speech recognition, http://www.chipstips.com/microblog/index.php/post/78/
Comment by Sterling Camden — March 2, 2006 @ 2:55 pm PST
[…] TDavid was just talking about voice recognition yesterday and the state of the “art” of software’s understanding of human verbiage. Later, I had to call Qwest because I recently switched back to them for land-line (I never really liked Qwest, but they swear they have improved service, and for a $100 savings per month I’ll let them back up that claim), but my toll-free number was still being billed by my previous carrier. So I call the business customer help line, and of course a speech-recognition engine answers the phone, using the voice of a twenty-something male with slightly over-regulated testosterone. […]
Pingback by Chip’s Quips » Blog Archive » Software Spirit of Service — May 9, 2006 @ 4:32 pm PST