<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 3.2//EN">
<HTML>
<HEAD>
<META HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=us-ascii">
<META NAME="Generator" CONTENT="MS Exchange Server version 6.5.6944.0">
<TITLE>Summary: Automatic phonetic transcription tool</TITLE>
</HEAD>
<BODY>
<!-- Converted from text/rtf format -->
<P><FONT SIZE=2 FACE="Arial">Hello,</FONT>
</P>
<P><FONT SIZE=2 FACE="Arial">Last week I posted an inquiry about the availability of automatic phonetic transcription systems for English. Thanks to everyone who responded. Here's a brief summary.</FONT></P>
<P><FONT SIZE=2 FACE="Arial">First off, there are many text to speech systems out there some of which may provide transcription indirectly. Also, lots of research has gone on in these area, but not all systems may be available online. The following are systems that I've been made aware of that provide text to phoneme transcription directly and are currently available for use.</FONT></P>
<P><FONT SIZE=2 FACE="Arial">Antal van den Bosch informed me of TreeTalk, which does grapheme-phoneme conversion for English and Dutch. There's an online demo here:</FONT></P>
<P><A HREF="http://ilk.uvt.nl/g2p-www-demo.html"><U><FONT COLOR="#0000FF" SIZE=2 FACE="Arial">http://ilk.uvt.nl/g2p-www-demo.html</FONT></U></A>
<BR><FONT SIZE=2 FACE="Arial">It is a decision-tree-based system and papers are referenced on the site. Further information is available here:</FONT>
<BR><A HREF="http://ilk.uvt.nl/~antalb/"><U><FONT COLOR="#0000FF" SIZE=2 FACE="Arial">http://ilk.uvt.nl/~antalb/</FONT></U></A>
<BR><FONT SIZE=2 FACE="Arial">It was built using TiMBL (</FONT><A HREF="http://ilk.uvt.nl/software.html"><U><FONT COLOR="#0000FF" SIZE=2 FACE="Arial">http://ilk.uvt.nl/software.html</FONT></U></A><FONT SIZE=2 FACE="Arial">) and is a part of NeXTeNS (</FONT><A HREF="http://nextens.uvt.nl/"><U><FONT COLOR="#0000FF" SIZE=2 FACE="Arial">http://nextens.uvt.nl/</FONT></U></A><FONT SIZE=2 FACE="Arial">), a Dutch text to speech system.</FONT></P>
<P><FONT SIZE=2 FACE="Arial">Kevin Lenzo at CMU has a rule-based, decision-tree system called t2p.</FONT>
<BR><A HREF="http://www-2.cs.cmu.edu/~lenzo/t2p/"><U><FONT COLOR="#0000FF" SIZE=2 FACE="Arial">http://www-2.cs.cmu.edu/~lenzo/t2p/</FONT></U></A>
<BR><FONT SIZE=2 FACE="Arial">I believe it is extendable to other languages, given a pronunciation dictionary. It's used by several full text to speech systems. It produces phonemes in the same encoding as the CMU Pronunciation Dictionary. Papers are referenced on the web site.</FONT></P>
<P><FONT SIZE=2 FACE="Arial">The speech group at NIST has a website with several tools including one by William Fisher called addttp4. It uses a combination of statistics and rules.</FONT></P>
<P><A HREF="http://www.nist.gov/speech/tools/index.htm"><U><FONT COLOR="#0000FF" SIZE=2 FACE="Arial">http://www.nist.gov/speech/tools/index.htm</FONT></U></A>
<BR><FONT SIZE=2 FACE="Arial">It's an English system and generates Pronlex entries in CMU format. The algorithm is described in:</FONT>
<BR><FONT SIZE=2 FACE="Arial">"A Statistical Text-to-Phone Function Using Ngrams and Rules", by William M. Fisher, IEEE International Conference on Acoustics, Speech, and Signal Processing 1999, pp. II-649-652.</FONT></P>
<P><FONT SIZE=2 FACE="Arial">The comp.speech newsgroup FAQ mentions an English system based on the Naval Research Lab's set of text to phoneme rules and put together by John A. Wasser.</FONT></P>
<P><A HREF="http://www.speech.cs.cmu.edu/comp.speech/Section5/Synth/text.phoneme.3.html"><U><FONT COLOR="#0000FF" SIZE=2 FACE="Arial">http://www.speech.cs.cmu.edu/comp.speech/Section5/Synth/text.phoneme.3.html</FONT></U></A>
<BR><FONT SIZE=2 FACE="Arial">The links on the FAQ aren't up to date. The system is now available here:</FONT>
<BR><A HREF="ftp://svr-ftp.eng.cam.ac.uk/pub/comp.speech/synthesis/english2phoneme.tar.gz"><U><FONT COLOR="#0000FF" SIZE=2 FACE="Arial">ftp://svr-ftp.eng.cam.ac.uk/pub/comp.speech/synthesis/english2phoneme.tar.gz</FONT></U></A>
<BR><FONT SIZE=2 FACE="Arial">The readme is dated 1985, and the files' modification dates are 1994, but it built OK with gcc 3.3. The phonetic codes it produces are documented in the source files. I couldn't find out much more information about this one.</FONT></P>
<P><FONT SIZE=2 FACE="Arial">Here's a site that has a CGI transcription system. Additional information and links on the site. </FONT>
<BR><A HREF="http://www.foreignword.com/dictionary/truespel/transpel.htm"><U><FONT COLOR="#0000FF" SIZE=2 FACE="Arial">http://www.foreignword.com/dictionary/truespel/transpel.htm</FONT></U></A>
</P>
<P><FONT SIZE=2 FACE="Arial">Also, of interest are dictionaries and wordlists that provide pronunciation guides. There are several dictionaries available on-line. However, CMU's Pronunciation Dictionary for English appears to be a good, machine-readable one. It's included with t2p, mentioned above.</FONT></P>
<P><A HREF="http://www.speech.cs.cmu.edu/cgi-bin/cmudict"><U><FONT COLOR="#0000FF" SIZE=2 FACE="Courier New">http://www.speech.cs.cmu.edu/cgi-bin/cmudict</FONT></U></A>
</P>
<P><FONT SIZE=2 FACE="Arial">Thanks again for the help!</FONT>
<BR><FONT COLOR="#800000" FACE="Arial">_________________________________</FONT>
<BR><B><FONT SIZE=2 FACE="Arial">Daniel Walker</FONT></B><FONT SIZE=1 FACE="Arial">, Software Engineer</FONT>
<BR><B><FONT COLOR="#800000" SIZE=2 FACE="Arial">Bowne Global Solutions</FONT></B>
</P>
<P><I><FONT COLOR="#000000" SIZE=1 FACE="Arial">Office </FONT></I> <FONT COLOR="#000000" SIZE=1 FACE="Arial">5095 Murphy Canyon Road</FONT>
<BR> <FONT COLOR="#000000" SIZE=1 FACE="Arial">San Diego, CA 92101 USA</FONT>
<BR><I><FONT COLOR="#000000" SIZE=1 FACE="Arial">Phone</FONT></I><FONT COLOR="#000000" SIZE=1 FACE="Arial"> +1 858 737 5247</FONT>
<BR><I><FONT COLOR="#000000" SIZE=1 FACE="Arial">Mobile </FONT></I> <FONT COLOR="#000000" SIZE=1 FACE="Arial">+1 619 251 4068</FONT>
<BR><I><FONT COLOR="#000000" SIZE=1 FACE="Arial">Fax</FONT></I> <FONT COLOR="#000000" SIZE=1 FACE="Arial">+1 858 737 5297</FONT>
<BR><U><FONT COLOR="#0000FF" SIZE=1 FACE="Arial">daniel.walker@bowneglobal.com</FONT></U>
<BR><U></U><A HREF="file://www.bowneglobal.com"><U><FONT COLOR="#0000FF" SIZE=1 FACE="Arial">www.bowneglobal.com</FONT></U></A><U></U>
</P>
<BR>
</BODY>
</HTML>