Napredna pretraga

Pregled bibliografske jedinice broj: 655485

An Overview of Prosodic Modelling for Croatian Speech Synthesis


Načinović Prskalo, Lucia; Martinčić-Ipšić, Sanda
An Overview of Prosodic Modelling for Croatian Speech Synthesis // 5th International Conference on Information Technologies and Information Society -ITIS 2013 / Levnajić, Zoran (ed). - Novo mesto, Slovenija : Faculty of Information Studies in Novo mesto, 2013. 105-112. / Levnajić, Zoran (ur.).
Novo mesto: Faculty of Information Studies, 2013. str. 105-112 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


Naslov
An Overview of Prosodic Modelling for Croatian Speech Synthesis

Autori
Načinović Prskalo, Lucia ; Martinčić-Ipšić, Sanda

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

Izvornik
5th International Conference on Information Technologies and Information Society -ITIS 2013 / Levnajić, Zoran (ed). - Novo mesto, Slovenija : Faculty of Information Studies in Novo mesto, 2013. 105-112. / Levnajić, Zoran - Novo mesto : Faculty of Information Studies, 2013, 105-112

Skup
5th International Conference on Information Technologies and Information Society -ITIS 2013

Mjesto i datum
Novo mesto, Slovenija, 7.-9.11.2013

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Prosody modelling; speech synthesis; TTS; duration models; F0 contour models; prosodic characteristics of Croatian

Sažetak
In order to include prosody into the text to speech (TTS)systems prosody knowledge needs to be acquired, represented and incorporated. Two main features of prosody important for modelling prosody for TTS systems are duration and F0 contour. There are various approaches to modelling those features and they can be categorized into three main groups: rule based, statistical and minimalistic. Some of the best known approaches to duration acquiring are Klatt’ s model, classification and regression trees (CARTS) and neural networks and to F0 modelling TOBI, Fujisaki and Tilt. A procedure for automatic intonation event detection on Croatian texts based on the Tilt model was evaluated in terms of Root Mean Square Error values for generated F0 contours.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Informacijske i komunikacijske znanosti



POVEZANOST RADA


Projekt / tema
318-0361935-0852 - Govorne tehnologije (Ivo Ipšić, )

Ustanove
Sveučilište u Rijeci - Odjel za informatiku