Re: [lojban] a beginner's questions

["randl.nortmn." <lojbanlists@wonderclown.com>]

On Wed, Jan 02, 2002 at 12:58:16PM +0100, Candide Kemmler wrote:
[...]
> That being said, I'm very curious about what drives other lojbanists' 
> motivation.
[...]

I've started studying it because it's just remarkably cool, in a geeky
sort of way.  (I'm using the positive connotation of "geek" here.)  If
it helps me think more clearly and logically, I'll call that a bonus.
If in a few years I can use it to control my PDA/wearable, awesome.
If it becomes a practical international language, I'll be happy,
though all those pigs flying about might be a bit of a nuisance. ;-P
But simply learning the language is enough motivation for me.

> - build a  lojban voice synthesizer (there's an open source C and Java 
> implementation of a voice synthesizer that seems low-level enough to 
> build what they call "voices" for new languages:
> -> http://freetts.sourceforge.net/docs/index.html).

I looked into this myself a few months ago.  It should be fairly
straightforward; from what I can tell, two things need to be done to
get any of the several freely-available TTS (text to speech) engines
to speak Lojban:

   1) Write some code that converts written text to phonetic
      representation (diphones or phenomes, including stress and pause
      markers).  For many languages this is very challenging, but for
      Lojban it should be trivial.

   2) Record and process lots of voice samples containing all the
      basic sounds of the language in all their possible 2-sound
      combinations.  (The combinations are necessary in order to get
      the transitions.)  This is the time-consuming part.  It should
      be done entirely by one speaker.

      Alternatively, find a voice recorded for another language that
      has all the same sounds as Lojban.  English won't work (doesn't
      have Lojban's 'x').  The resulting voice will sound a lot like
      the language the voice was originally prepared for.

I would be interested in helping out on such a project.  Specifically,
I'll handle the first part (the easy part) if somebody will get the
recordings together for the second part.

> - build a lojban voice recognition framework (there's a sourceforge 
> project on voice recognition (not much yet though):
> -> http://sourceforge.net/projects/cmusphinx/).

I don't know much about this, but it should also be fairly easy; much
easier than for most natural languages.  In fact, most of the effort
would probably be wading through all the unneccessary parts of
cmusphinx to get to the parts that are needed.

If both of these were available (TTS and voice recognition), it would
become possible to create some very nice Lojban teaching software that
drilled on verbal skills as well as written, which would be
marvellously helpful, given that most students of Lojban rarely or
never have verbal contact with other speakers.  And #lojban IRC chats
could be spoken aloud as well.  Anybody that goes to the effort of
completing step #2 above with their own voice would even have the
honor of having his own voice used for speaking his IRC statements to
other channel members. ;-)

mu'omi'e randl.