Re: IPA speech synthesizer

On Thu, 19 Feb 2009 10:41:24 -0800, Sai Emrys <sai@...> wrote:

>Surely someone has made an IPA synthesizer by now?
I've certainly looked before, but not found anything really convincing.
There are, for instance,

http://newsgroups.derkeiler.com/Archive/Comp/comp.speech.research/2005-07/msg00024.html
  http://www.asel.udel.edu/speech/tutorials/synthesis/Klatt.html
  http://answers.yahoo.com/question/index?qid=20080829002936AAGytpq
but the second I don't know how to use, the first is limited to English
phones and the third may be as well.

A lot of text-to-speech stuff uses IPA or something like that as an
intermediate -- so we might be in the irritating situation that an IPA
synthesiser does exist but we can't use it, because it's bound too tightly
to the orthography-interpreting front end.

>And: how kludgy would it be if we just took a bunch of IPA samples -
>e.g. from http://www.phonetics.ucla.edu/course/chapter1/chapter1.html
>- and mashed 'em back to back?
Fairly kludgy AIUI.  I think you want a library of bigrams for that to sound
half decent.

Alex