Databases of Heterogeneous Segments for Concatenative Speech Synthesis
Ivan Kopeček (Faculty of Informatics, Masaryk University Brno, Botanicka 68a, 602 00 Brno Czech Republic)
Karel Pala (Faculty of Informatics, Masaryk University Brno, Botanicka 68a, 602 00 Brno Czech Republic)
SP1: Speech Resources
Heterogeneous segments can enhance the quality of concatenative speech synthesis especially for highly inflected languages. In this paper we present a brief analysis of the segment types on a general level and discuss the problems related to optimising databases of heterogeneous segments. We present a brief discussion of the algorithmical complexity for the proposed approach and offer some heuristics for optimizing databases of heterogeneous segments. We also mention the syllable and morphemic segments in relation to the development of the Czech speech synthesis system Demosthenes.
Concatenative speech synthesis