Title: Slovak text-to-speech synthesis in ARTIC system
Other Titles: Slovenská syntĂ©za Ĺ™eÄŤi z textu v systĂ©mu ARTIC
Authors: Matoušek, Jindřich
Tihelka, Daniel
Citation: MATOUĹ EK, JindĹ™ich; TIHELKA, Daniel. Slovak text-to-speech synthesis in ARTIC system. In: Text, speech and dialogue. Berlin: Springer, 2004, p. 155-162. (Lectures notes in computer science; 3206). ISBN 3-540-23049-1.
Issue Date: 2004
Publisher: Springer
Document type: článek
article
URI: http://www.kky.zcu.cz/cs/publications/MatousekJ_2004_Slovaktext-to-speech
http://hdl.handle.net/11025/17026
ISBN: 3-540-23049-1
Keywords: syntĂ©za Ĺ™eÄŤi;syntĂ©za Ĺ™eÄŤi;inventář akustickĂ˝ch jednotek;segmentace Ĺ™eÄŤi;slovenština;vĂ­cejazyÄŤnĂ˝ TTS systĂ©m;ARTIC;HMM
Keywords in different language: speech synthesis;speech synthesis;acoustic unit inventory;segmentation of speech;slovak language;multilingual TTS system;ARTIC;HMM
Abstract: V tomto ÄŤlánku je pĹ™edstaven zbrusu novĂ˝ systĂ©m slovenskĂ© syntĂ©zy Ĺ™eÄŤi z textu. Byl vyvinut v rámci systĂ©mu ARTIC, pĹŻvodnÄ› navrĹľenĂ©ho k syntĂ©ze ÄŤeskĂ© Ĺ™eÄŤi, s vyĹľitĂ­m znalostĂ­ slovenskĂ©ho jazyka. K plnÄ› automatickĂ©mu vytvoĹ™enĂ­ inventáře akustickĂ˝ch jednotek slovenskĂ©ho jazyka byl pouĹľit statistickĂ˝ přístup, využívajĂ­cĂ­ skrytĂ© Markovovy modely. Pro pĹ™evedenĂ­ vstupnĂ­ho textu do fonetickĂ© podoby a k odhadu suprasegmentálnĂ­ch charakteristik jsme navrhli fonetická a prozodická transkripÄŤnĂ­ pravidla. VĂ˝sledkem je plnÄ› funkÄŤnĂ­ TTS systĂ©m pĹ™evádÄ›jĂ­cĂ­ libovolnĂ˝ slovenskĂ˝ text na odpovĂ­dajĂ­cĂ­ Ĺ™eÄŤ. NeformálnĂ­ poslechovĂ© testy ukazujĂ­, Ĺľe systĂ©m umĂ­ vytvářet vysoce kvalitnĂ­ Ĺ™eÄŤ.
Abstract in different language: This paper presents a brand-new Slovak text-to-speech system. It was developed within the framework of ARTIC system (primarily designed to synthesize Czech speech) with respect to the knowledge of Slovak language. Thus, statistical approach (using hidden Markov models) was employed to build an acoustic unit inventory of Slovak language in a fully automatic way. Both phonetic transcription and prosodic rules were proposed to convert an input text to its phonetic form and to estimate its suprasegmental features. As a result, a fully working text-to speech system that converts an arbitrary Slovak text to the corresponding output speech was designed. The informal listening tests show the system is capable of producing speech of a high quality (with high level of intelligibility and good naturalness).
Rights: Â© JindĹ™ich Matoušek - Daniel Tihelka
Appears in Collections:Články / Articles (NTIS)
Články / Articles (KIV)

Files in This Item:
File Description SizeFormat 
MatousekJ_2004_Slovaktext-to-speech.pdfPlný text142,73 kBAdobe PDFView/Open


Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/17026

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.