[Kde-accessibility] KTTS

[Paul Giannaros]

If you felt bored you could write a script to convert the text to SSML
with the write pronunciation. At the end of the day, you can take as
much text around the word into context and still get the wrong
outcome. Maybe it just isn't worth the resources and time trying to.

On Thu, 23 Dec 2004 16:19:55 +0000, Paul Giannaros
<ceruleanblaze at gmail.com> wrote:
> If you felt bored you could write a script to convert the text to SSML
> with the write pronunciation. At the end of the day, you can take as
> much text around the word into context and still get the wrong
> outcome. Maybe it just isn't worth the resources and time trying to.
> 
> 
> On Thu, 23 Dec 2004 08:07:32 -0500, Gary Cramblitt
> <garycramblitt at comcast.net> wrote:
> > On Thursday 23 December 2004 06:41 am, Robert Moore wrote:
> > > Hello there,
> > >
> > > How might the application be enhanced to distinguish two tenses or
> > > different pronunciations of the same word?
> > >
> > > For example, in the English words for the verb "to read": "I had read
> > > articles but now I can also listen to them" and "I like to read".
> > >
> > > Does the synth know the tense it is speaking? If not, could it?
> >
> > It is up to the synth.  Festival, for example, does do part of speech
> > analysis.  If it gets it wrong, it is possible to override using SSML.
> >
> >  <speak>
> >  <p>I went down to 32 chocolate <pron sub="street">st.</pron></p>
> >  </speak>
> >
> > Otherwise, this is outside the scope of KTTS.
> > --
> > Gary Cramblitt (aka PhantomsDad)
> > KDE Text-to-Speech Maintainer
> > http://accessibility.kde.org/developer/kttsd/index.php
> > _______________________________________________
> > kde-accessibility mailing list
> > kde-accessibility at kde.org
> > https://mail.kde.org/mailman/listinfo/kde-accessibility
> >
>