15th International Congress of Phonetic Sciences (ICPhS-15)

Barcelona, Spain
August 3-9, 2003


A Comparative Description of GtoP modules for Portuguese and Mirandese Using Finite State Transducers

D. Caseiro (1), Isabel Trancoso (1), C. Viana (2), M. Barros (2)

(1) INESC-ID/IST, Portugal
(2) CLUL, Portugal

Mirandese is the second official language in Portugal. For ages it was only preserved as an oral language and it was the object of a recent orthographic convention. This paper describes our efforts in porting our grapheme-to-phone module from European Portuguese to Mirandese. We describe the main differences between the two languages that can affect this module and the set of new SAMPA symbols that had to be defined for the phonetic transcription of Mirandese. We then briefly cover our rule formalism and the composition of the various transducers involved in the grapheme-to-phone conversion, and describe the results obtained for the two languages. The use of .nite state transducers allowed a very flexible and modular framework for deriving and testing new rule sets. Our experience led us to believe that grapheme-to-phone modules could be helpful tools for researchers involved in the establishment of orthographic conventions for other oral transmission languages.

Full Paper

Bibliographic reference.  Caseiro, D. / Trancoso, Isabel / Viana, C. / Barros, M. (2003): "A comparative description of gtop modules for Portuguese and Mirandese using finite state transducers", In ICPhS-15, 2605-2608.