Govorec (Speaker) - Slovenian Text-To-Speech Synthesizer for Various Applications

摘要

This paper presents a new text-to-speech (ITS) system called Speaker (Govorec) that is capable of automatic conversion of any Slovenian text into speech. The different phases of the synthesis task are performed by several sequentially operating independent modules (text analysis, prosody generation and segmental concatenation), which are pipelined together. With enhancements to the first module the weakest point of previous synthesizer has been eliminated, that is the correct lexical stress assignment of words. Higher naturalness and agitation of synthetic speech is achieved mainly with different transformations between labelled speech corpus and concrete text, which is synthesised. The system is used by members of the Slovenian Foundation for the Blind and Visually impaired and was awarded with the first price for innovation in the field of life improvements for handicapped people. Currently, several leading Slovenian telecommunication companies are testing the system for providing information (e-mail, SMS, weather reports, traffic information) through mobile phones.