DocumentCode :
3621929
Title :
Obtaining Prosodic Information from Text in Serbian Language
Author :
M.S. Secujski
Author_Institution :
Faculty of Engineering, University of Novi Sad, Trg Dositeja Obradovica 6, 21000 Novi Sad, Serbia &
Volume :
2
fYear :
2005
fDate :
6/27/1905 12:00:00 AM
Firstpage :
1654
Lastpage :
1657
Abstract :
In this paper a rule based strategy for automatic accent assignment and obtaining prosodic information from plain text in Serbian language is described. The strategy takes into account most of the peculiarities of Serbian language that prove challenging to speech synthesis, enabling production of highly intelligible and natural sounding synthesized speech
Keywords :
"Speech synthesis","Natural languages","Tagging","Dictionaries","Stress","Timbre","Speech analysis","Synthesizers","Protection","Knowledge engineering"
Publisher :
ieee
Conference_Titel :
Computer as a Tool, 2005. EUROCON 2005.The International Conference on
Print_ISBN :
1-4244-0049-X
Type :
conf
DOI :
10.1109/EURCON.2005.1630288
Filename :
1630288
Link To Document :
بازگشت