Newsgroups: comp.speech
Path: pavo.csi.cam.ac.uk!doc.ic.ac.uk!agate!howland.reston.ans.net!news.moneng.mei.com!uwm.edu!msuinfo!harbinger.cc.monash.edu.au!bunyip.cc.uq.oz.au!pandora!sysseh
From: sysseh@devetir.qld.gov.au (Steve Hocking)
Subject: Different phoneme sets.
Nntp-Posting-Host: orion.devetir.gov
Keywords: klatt, sun, CMU , phonemes.
Sender: usenet@devetir.qld.gov.au (Network News)
Organization: DEVETIR, QLD, AUSTRALIA
Date: Tue, 11 Jan 1994 02:03:56 GMT
Message-ID: <sysseh.758253836@pandora>
Summary: How dost thou convert?
Distribution: "world"
Lines: 12

	I've noticed that various of the PD packages available seem to use
different phoneme set for speech synthesis. I can quite easily convert
between the publicly available set of phonemes for Sun's and the ones used
in the CMU dictionary, but I do not have a mapping between those and the
richer set used in the klatt synthesiser. (I'm trying build a range of small
tools, each doing a specific job - one to look up words in a dictionary &
spit out the appropriate phonemes, another to "translate" phonemes, and
another to take those phonemes and "say" them). Any one have a clue?

--

	Stephen
