Skip to the main content

Original scientific paper

TEXT-TO-SPEECH SYNTHESIS: A PROTOTYPE SYSTEM FOR CROATIAN LANGUAGE

Miran POBAR ; Department for Informatics, University of Rijeci, Rijeka, Croatia
Sanda MARTINČIĆ-IPŠIĆ ; Department for Informatics, University of Rijeci, Rijeka, Croatia
Ivo IPŠIĆ ; Faculty of Engineering, University of Rijeka, Rijeka, Croatia


Full text: croatian pdf 681 Kb

page 31-44

downloads: 1.839

cite

Full text: english pdf 681 Kb

page 31-44

downloads: 781

cite


Abstract

This paper presents the development of a Croatian text-to-speech system capable of synthesizing speech from arbitrary text. Input text in normalized form is first transcribed into a phonetic string (grapheme-to-phoneme conversion) and then processed by a TD-PSOLA based synthesizer. A procedure for automatic selection of diphones from a spoken corpus is proposed. A Croatian language diphone database was built for the system. Subjective quality evaluations of the resulting speech were performed, as well as tests for intelligibility.

Keywords

diphone selection; Croatian diphone database; diphone concatenation; text-to-speech systems; speech quality evaluation

Hrčak ID:

30616

URI

https://hrcak.srce.hr/30616

Publication date:

19.12.2008.

Article data in other languages: croatian

Visits: 5.033 *