Title :
Croatian HMM based speech synthesis
Author :
S. Martincic-Ipsic;I. Ipsic
Author_Institution :
Dept. of Informatics, Univ. of Rijeka
fDate :
6/28/1905 12:00:00 AM
Abstract :
The paper describes the development of a trainable speech synthesis system, based on hidden Markov models. An approach to speech signal generation using a source-filter model is presented. Inputs into the synthesis system are speech utterances and their phone level transcriptions. A method using context dependent acoustic models and Croatian phonetic rules for speech synthesis is proposed. Croatian HMM based speech synthesis experiments are presented and generated speech results are discussed
Keywords :
"Hidden Markov models","Speech synthesis","Signal synthesis","Signal generators","Context modeling","Speech recognition","Application software","Humans","Production systems","Filters"
Conference_Titel :
Information Technology Interfaces, 2006. 28th International Conference on
Print_ISBN :
953-7138-05-4
DOI :
10.1109/ITI.2006.1708487
