Restricted unlimited domain synthesis

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 opendomain material. This dichotomy is also reflected in the speech database, which consists of a domain specific and an opendomain part. The text material for the open-domain part was constructed to optimize coverage of diphones and phonemes in different contexts.