Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!watmath!clyde!burl!mgnetp!ihnp4!zehntel!hplabs!sri-unix!DIKRAN@SU-CSLI.ARPA
From: DIKRAN@SU-CSLI.ARPA
Newsgroups: net.ai
Subject: Seminar - Speech Recognition Using Lexical Information
Message-ID: <652@sri-arpa.UUCP>
Date: Wed, 1-Aug-84 21:45:25 EDT
Article-I.D.: sri-arpa.652
Posted: Wed Aug  1 21:45:25 1984
Date-Received: Sun, 5-Aug-84 00:26:53 EDT
Lines: 28

From:  Dikran Karagueuzian 

         [Forwarded from the CSLI Newsletter by Laws@SRI-AI.]

  LEXICAL ACCESS USING PARTIAL INFORMATION

By Daniel P. Huttenlocher, Massachusetts Institute of
   Technology, Friday, August 3, 2 p.m. in the Trailers'
   Conference Room next to Ventura Hall.


ABSTRACT:  Current approaches to speech recognition rely on classical
pattern matching techniques which utilize little or no language knowledge.
We have recently proposed a model of word recognition which uses
speech-specific knowledge to access words on the basis of partial
information.   These partial descriptions serve to partition a large lexicon
into small equivalence classes  using sequential phonetic and prosodic
constraints.  The representation is attractive for speech recognition system
because it allows all but a small number of word candidates to be excluded
using only a crude description of the acoustic signal.  For example, if the
word ``splint'' is represented according to the broad phonetic string
[fricative][stop][liquid][vowel][nasal][stop], there are only two matching
words in the 20,000 word Webster's Pocket Dictionary, ``splint'' and ``sprint.''

Thus, a partial representation can both greatly reduce the space of possible
word candidates, and be relatively insensitive to variability in the speech
signal across utterance situations. This talk will discuss a set of studies
examining the power of such partial lexical representations.