> One gets into trouble if one won't exercise a little discipline > (speaking too fast, background noise, slurring words, using slang, etc.) > And even then, with just a single speaker, systems will learn to adapt, > and translate "y'wl" to the more proper "you-all".
... Siberian Huskies howling at me in the background because they expect me to feed them... <g>... I have had to take a strong stance re: not feeding the Huskies. They are so darned clever. They learned that if I am talking on the phone (or into a microphone perhaps?) that by howling and bitching about wanting food I would feed them snacks just to shut them up. I decided I was no longer going to be "the trained animal", and refused to feed them for a few weeks (only Lynda would feed them morning and evening), and explaining to whoever I was chatting with why they were hearing such nonsense in the background. They kind of learned to not howl (as much <g>), but from time to time they test me. Too smart for their own britches! So, your comment re: background noises is quite appropriate for my circumstances. Thank you! Gil > -----Original Message----- > From: [EMAIL PROTECTED] > [mailto:[EMAIL PROTECTED] Behalf Of Whil Hentzen (Pro*) > Sent: Friday, February 02, 2007 10:07 AM > To: [EMAIL PROTECTED] > Subject: Re: [NF] Speech-To-Text software opinions sought > > > >> Voice recognition is getting more and more accurate by the > day, but it is > >> important to realize that (1) it's still a very tough problem > to solve and > >> (2) there are parallel efforts attacking the problem. The > parallel tracks > >> are handling (1) an unlimited domain for a single speaker and (2) > >> a limited domain for any speaker. > > Dave's nailed it on the head. > > To add onto Dave's synopsis (I did a bit of looking into this about 25 > years, along with vision systems for robots), what Gil is looking for is > actually quite reasonably these days. The tales of woe are generally > from folks who have expectations beyond the current realm of technology. > > For a single person to train a system with a distinct vocab ("SQL" is a > language, not the followup to a hit movie), particularly with someone > who knows what they're doing and has the discipline to adapt a bit > (which fits Gil to a 't'), voice recog is definitely a reasonable > vehicle right now. > > One gets into trouble if one won't exercise a little discipline > (speaking too fast, background noise, slurring words, using slang, etc.) > And even then, with just a single speaker, systems will learn to adapt, > and translate "y'wl" to the more proper "you-all". > > Whil > > > [excessive quoting removed by server] _______________________________________________ Post Messages to: ProFox@leafe.com Subscription Maintenance: http://leafe.com/mailman/listinfo/profox OT-free version of this list: http://leafe.com/mailman/listinfo/profoxtech ** All postings, unless explicitly stated otherwise, are the opinions of the author, and do not constitute legal or medical advice. This statement is added to the messages for those lawyers who are too stupid to see the obvious.
