From nobody@digitalkingdom.org Wed Nov 15 08:01:07 2006 Received: with ECARTIS (v1.0.0; list lojban-list); Wed, 15 Nov 2006 08:01:08 -0800 (PST) Received: from nobody by chain.digitalkingdom.org with local (Exim 4.63) (envelope-from ) id 1GkNBm-0002FG-3v for lojban-list-real@lojban.org; Wed, 15 Nov 2006 08:00:38 -0800 Received: from eastrmmtao02.cox.net ([68.230.240.37]) by chain.digitalkingdom.org with esmtp (Exim 4.63) (envelope-from ) id 1GkNBZ-0002Ev-VX for lojban-list@lojban.org; Wed, 15 Nov 2006 08:00:37 -0800 Received: from eastrmimpo02.cox.net ([68.1.16.120]) by eastrmmtao02.cox.net (InterMail vM.6.01.06.03 201-2131-130-104-20060516) with ESMTP id <20061115160028.UBGG28530.eastrmmtao02.cox.net@eastrmimpo02.cox.net> for ; Wed, 15 Nov 2006 11:00:28 -0500 Received: from [127.0.0.1] ([72.192.234.183]) by eastrmimpo02.cox.net with bizsmtp id n3zU1V0083y5FKc0000000; Wed, 15 Nov 2006 10:59:30 -0500 Message-ID: <455B3996.5070301@lojban.org> Date: Wed, 15 Nov 2006 11:00:22 -0500 From: Bob LeChevalier User-Agent: Mozilla Thunderbird 1.0.7 (Windows/20050923) X-Accept-Language: en-us, en MIME-Version: 1.0 To: lojban-list@lojban.org Subject: [lojban] Re: is there a phonologist in the house? References: <455B22D6.7040101@ropine.com> In-Reply-To: <455B22D6.7040101@ropine.com> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit X-Spam-Score: -2.6 (--) X-archive-position: 13183 X-ecartis-version: Ecartis v1.0.0 Sender: lojban-list-bounce@lojban.org Errors-to: lojban-list-bounce@lojban.org X-original-sender: lojbab@lojban.org Precedence: bulk Reply-to: lojban-list@lojban.org X-list: lojban-list Seth Gordon wrote: > The whole discussion of mandatory pauses and audio-visual isomorphism > reminds me of how speech-recognition software, back when I was paying > attention to such things, required ... you ... to ... pause ... between > ... words in order to understand what you were saying. > > If I understand correctly, 21st-century speech-recognition software does > not require this. Are they doing this by simply matching the speech > stream against some kind of dictionary in order to guess where the word > breaks are, or are there subtle changes in pronounciation that people > use to mark word boundaries even in connected speech? What I was told a couple of years ago, is that later speech recognition was not merely phonological, but relied on dictionaries and grammar as well. (I believe that there was some interest at Dragon Systems in Lojban speech recognition, but it would have required money that no one had). lojbab To unsubscribe from this list, send mail to lojban-list-request@lojban.org with the subject unsubscribe, or go to http://www.lojban.org/lsg2/, or if you're really stuck, send mail to secretary@lojban.org for help.