Newsgroups: comp.speech
Path: pavo.csi.cam.ac.uk!doc.ic.ac.uk!agate!pasteur!bregler
From: bregler@ICSI.Berkeley.EDU (Chris Bregler)
Subject: Re: Lip-reading - time required to start utterance recognition
Message-ID: <1993Aug2.175143.22633@pasteur.Berkeley.EDU>
Sender: nntp@pasteur.Berkeley.EDU (NNTP Poster)
Nntp-Posting-Host: icsib70.icsi.berkeley.edu
Organization: International Computer Science Institute, Berkeley, CA, U.S.A.
References: <1993Aug2.114543.7304@dct.ac.uk>
Date: Mon, 2 Aug 1993 17:51:43 GMT
Lines: 15

There are people active in Automatic Lipreading at University of Karlsruhe,
ICSI, and Ricoh. Here's one of our reference: 

C.Bregler, H.Hild, S.Manke, and A.Waibel, "Improving Connected Letter 
Recognition by Lipreading", Proc. ICASSP, Minneapolis 1993

In article <1993Aug2.114543.7304@dct.ac.uk>, McRamm <mcramm@dct.ac.uk> wrote:
>
>
>I'm curious to know if anyone has done any work on lip-reading. Specifically
>how long it takes a proficient lip-reader to start recognising utterances. (In
>machine terms - how many video frames at a 25fps rate say, it takes before the
>lip-reader is able to make a first guess at the utterance).


