[Corpora-List] Croatian Corpus

[Danko Sipka]

Croatian National Corpus is at:

http://www.hnk.ffzg.hr/cnc.htm

Best,

Danko Sipka
Research Associate Professor and Associate Director
Critical Languages Institute (http://www.asu.edu/cli)
Arizona State University
E-mail: Danko.Sipka at asu.edu
Web: http://www.public.asu.edu/~dsipka
Phone: 480-965-7706
Fax: 480-965-0310

----- Original Message -----
From: "Anthony Weaver" <aweaver at cs.sunysb.edu>
To: <CORPORA at HD.UIB.NO>
Sent: Wednesday, April 09, 2003 9:13 AM
Subject: [Corpora-List] Croatian Corpus


>
> I am doing some speech recognition for Croatian and I would like
> to know if there is a freely available corpus for Croatian?  I am
> specifically looking for a text corpus, maybe no smaller than about 20K
> words.
>
>  I would also like to know if there are any papers discussing Croatian
pronunciation?
> More specifically, it has been explained to me by a native speaker, and on
> various sites on the web that Croatian pronunciation is mostly
> unambiguous, but I have been unable to find any papers/research that would
> support or refute this claim.  In English, each letter can have multiple
> pronunciations, but this does not seem to occur for Croatian.  All help is
> greatly appreciated.
>
> Tony
>