In this article, a methodology is presented regarding the design of a segment database for use with a time-domain speech synthesis system for the Greek language. The main issue of this process is the systematic generation of a corpus containing all possible instances of the segments for the specific language. Particular issues such as the phonetic coverage, the sentence selection as well as iterative evaluation techniques employing custom-built tools are discussed. The resulting corpus is characterised by a near-minimal size, provides a complete coverage of the Greek language and its distribution of phonemes is similar to that of natural corpora. A typical spoken acquisition procedure may then be performed, resulting in a segment database for use with a time-domain Greek synthesizer. The corpus creation procedure allows for the fine-tuning of the segment database's language-dependent characteristics and thus assists in the generation of high-quality text-to-speech synthesis.
Cite as: Fotinea, S.-E.F., Tambouratzis, G.D., Carayannis, G.V. (2001) Constructing a segment database for greek time domain speech synthesis. Proc. 7th European Conference on Speech Communication and Technology (Eurospeech 2001), 2075-2078, doi: 10.21437/Eurospeech.2001-490
@inproceedings{fotinea01_eurospeech,
author={Stavroula-Evita F. Fotinea and George D. Tambouratzis and George V. Carayannis},
title={{Constructing a segment database for greek time domain speech synthesis}},
year=2001,
booktitle={Proc. 7th European Conference on Speech Communication and Technology (Eurospeech 2001)},
pages={2075--2078},
doi={10.21437/Eurospeech.2001-490}
}