Naslov
Normalization of Non-Standard Words in Croatian Texts

Autori
Beliga, Slobodan ; Pobar, Miran ; Martinčić-Ipšić, Sanda

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Text, Speech and Dialogue extension to Lecture Notes in Artificial Intelligence LNAI6836 / Hebernal, Ivan ; Matoušek, Vaclav - Plzeň : University of West Bohemia, 2011, 1-8

ISBN
987-80-261-0069-0

Skup
Text, Speech and Dialogue

Mjesto i datum
Plzeň, Češka Republika, 01.09.2011. - 05.09.2011

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
text normalization; non-standard words; text-to-speech

Sažetak
This paper presents text normalization which is an integral part of any text-to-speech synthesis system. Text normalization is a set of methods with a task to write non-standard words, like numbers, dates, times, abbreviations, acronyms and the most common symbols, in their full expanded form. The whole taxonomy for classification of non-standard words in Croatian language together with rule-based normalization methods combined with a lookup dictionary are proposed. Achieved token rate for normalization of Croatian texts is 95%, where 80% of expanded words are in correct morphological form.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Informacijske i komunikacijske znanosti

Napomena
Student Section

POVEZANOST RADA