This paper describes the hybrid unit selection strategy for restricted domain synthesis in the SmartKom dialog system. Restricted domains are characterized as being biased toward domain specific utterances while being unlimited in terms of vocabulary size. This entails that unit selection in restricted domains must deal with both domain specific and open-domain material. The strategy presented here combines the advantages of two existing unit selection approaches, motivated by the claim that the phonological structure matching approach is advantageous for domain specific parts of utterances, while the acoustic clustering algorithm is more appropriate for open-domain material. This dichotomy is also reflected in the speech database, which consists of a domain specific and an open-domain part. The text material for the open-domain part was constructed to optimize coverage of diphones and phonemes in different contexts.
Cite as: Schweitzer, A., Braunschweiler, N., Klankert, T., Möbius, B., Sauberlich, B. (2003) Restricted unlimited domain synthesis. Proc. 8th European Conference on Speech Communication and Technology (Eurospeech 2003), 1321-1324, doi: 10.21437/Eurospeech.2003-134
@inproceedings{schweitzer03_eurospeech,
author={Antje Schweitzer and Norbert Braunschweiler and Tanja Klankert and Bernd Möbius and Bettina Sauberlich},
title={{Restricted unlimited domain synthesis}},
year=2003,
booktitle={Proc. 8th European Conference on Speech Communication and Technology (Eurospeech 2003)},
pages={1321--1324},
doi={10.21437/Eurospeech.2003-134}
}