<!doctype html public "-//w3c//dtd html 4.0 transitional//en">

<html>

VSWarren@aol.com wrote:

<blockquote TYPE=CITE>Can anyone please suggest either a program to convert

from orthographic to

<br>phonemic or alternatively a large corpora where phonemic transcriptions

are

<br>given for such a large number of different words.</blockquote>

<p><br>  You can download software that does a pretty good job

<br>of converting text to segmental phonemes from the NIST

<br>website: see <A HREF="http://www.nist.gov/speech/tools/index.htm">http://www.nist.gov/speech/tools/index.htm</A>.

<br>But you should be aware that the output from this is

<br>phonemic underlying forms that often are realized differently

<br>in actual speech; for instance, what usually surfaces as

<br>syllabic consonants are phonemicized as a sequence of

<br>(zero-stressed) schwa plus consonant (as in "button").

<p>  A good <i>free </i>lexicon of English is available from CMU;

<br>see <A HREF="http://www.speech.cs.cmu.edu/cgi-bin/pronounce">http://www.speech.cs.cmu.edu/cgi-bin/pronounce</A>.

<br>In addition, the LDC offers a high-accuracy one, but

<br>it's not free.  And Joe Picone & Co. of Mississippi State

<br>are making available lexicons derived from their

<br>re-transcription of the Switchboard corpus along with

<br>phonetic transcriptions from ICSI; see

<br><A HREF="http://www.isip.msstate.edu/projects/switchboard/index.html">http://www.isip.msstate.edu/projects/switchboard/index.html</A>.

<p> - Bill F.

<br> 

<br> </html>