Pregled bibliografske jedinice broj: 309196
Croatian HMM-based Speech Synthesis
Croatian HMM-based Speech Synthesis // CIT. Journal of computing and information technology, 14 (2006), 4; 307-313 (podatak o recenziji nije dostupan, članak, znanstveni)
CROSBI ID: 309196 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Croatian HMM-based Speech Synthesis
Autori
Sanda, Martinčić - Ipšić ; Ivo, Ipšić
Izvornik
CIT. Journal of computing and information technology (1330-1136) 14
(2006), 4;
307-313
Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni
Ključne riječi
corpus based speech synthesis; hidden Markov models; context-dependent acoustic modelling; Croatian speech corpora
Sažetak
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.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
POVEZANOST RADA
Projekti:
009-0361935-0852 - Govorne tehnologije
Ustanove:
Filozofski fakultet, Rijeka
Citiraj ovu publikaciju:
Uključenost u ostale bibliografske baze podataka::
- The INSPEC Science Abstracts series
