Pregled bibliografske jedinice broj: 261712
Context-Dependent Acoustic Modelling of Croatian Speech
Context-Dependent Acoustic Modelling of Croatian Speech // Proceedings of 5th Slovenian and 1st international Language Technologies Conference 2006 IS-LTC'06 / Gros, Jerneja ; Erjavec, Tomaž (ur.).
Ljubljana: Institut Jožef Stefan, 2006. str. 251-257 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 261712 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Context-Dependent Acoustic Modelling of Croatian Speech
Autori
Martinčić-Ipšić, Sanda ; Ipšić, Ivo
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings of 5th Slovenian and 1st international Language Technologies Conference 2006 IS-LTC'06
/ Gros, Jerneja ; Erjavec, Tomaž - Ljubljana : Institut Jožef Stefan, 2006, 251-257
Skup
Proceedings of 5th Slovenian and 1st international Language Technologies Conference
Mjesto i datum
Ljubljana, Slovenija, 09.10.2006. - 10.10.2006
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
speech recognition; . speech synthesis; acoustic modelling; HMM
Sažetak
This paper presents experiments of Croatian speech modelling used in speech recognition as well as in speech synthesis. The proposed acoustic model is based on context-dependent triphone hidden Markov models and Croatian phonetic rules. For speech recognition and speech synthesis experiments a common Croatian speech corpora is used. The experiments have shown that Croatian speech corpora, Croatian phonetic rules and hidden Markov models as the modelling formalism can be used to develop speech recognition and speech synthesis systems in parallel. The proposed procedures for Croatian acoustic modelling were developed as speech interfaces in a spoken dialog system.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo
