Re: [lojban] speech synthesizer

[Avital Oliver <olivera@macs.biu.ac.il>]

On Thu, 15 Feb 2001, Arnt Richard Johansen wrote:

> >Please have a look at the
> >OpenSource SpeechSynthesizer 1.1. web page:
> > http://hyperdrive.media.mit.edu/cgi-bin/stefanm/synth
> >They are building a collection of sounds for a number of languages.
> >The list of languages includes Lojban!
> >
> >Anyone cares to help them?
> 
> I was bored yesterday, so I recorded about 40 words.I added most of them
> today, except "je'e", "na'e", "li'u", and "u'i", because they ended up as
> "je", "na", "li", and "u" in the sample directory, respectively.The
> maintainer has been notified.
> 

Isn't this somewhat, well, not the way to do it, regarding Lojban's
phonology/morphology? I mean, it would be much easier just to program
simple syllable-making functions, and let the program do the (amazing
difficult) task of splitting the words into syllables. I mean, you can't
teach the program all lujvo, or all fu'ivla, or even all cmavo
combinations.